Embed Size (px)
DESCRIPTION
Software and model selection challenges in meta-analysis: MetaEasy, model assumptions, homogeneity and IPD
Citation preview
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
Software and model selection challenges inmeta-analysis
MetaEasy, model assumptions, homogeneity and IPD
Evan Kontopantelis David Reeves
Centre for Primary CareInstitute of Population Health
University of Manchester
Health Methodology Research SeminarManchester, 6 Nov 2012
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
Outline
1 Meta-analysis overview
2 Two-stage meta-analysis
3 One-stage meta-analysis
4 Summary
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
The heterogeneity issue
Outline
1 Meta-analysis overview
2 Two-stage meta-analysis
3 One-stage meta-analysis
4 Summary
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
The heterogeneity issue
Timeline
‘Meta’ is a Greek preposition meaning ‘after’, someta-analysis =⇒ post-analysisEfforts to pool results from individual studies back as far as1904The first attempt that assessed a therapeutic interventionwas published in 1955In 1976 Glass first used the term to describe a "statisticalanalysis of a large collection of analysis results fromindividual studies for the purpose of integrating thefindings"
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
The heterogeneity issue
Meta-analysing reported study results
A two-stage processthe relevant summary effect statistics are extracted frompublished papers on the included studiesthese are then combined into an overall effect estimateusing a suitable meta-analysis model
However, problems often arisepapers do not report all the statistical information requiredas inputpapers report a statistic other than the effect size whichneeds to be transformed with a loss of precisiona study might be too different to be included (populationclinically heterogeneous)
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
The heterogeneity issue
Individual Patient DataIPD
These problems can be avoided when IPD from eachstudy are available
outcomes can be easily standardisedclinical heterogeneity can be addressed with subgroupanalyses and patient-level covariate controlling
Can be analysed in a single- or two-stage processmixed-effects regression models can be used to combineinformation across studies in a single stagethis is currently the best approach, with the two-stagemethod being at best equivalent in certain scenarios
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
The heterogeneity issue
Outline
1 Meta-analysis overviewThe heterogeneity issue
2 Two-stage meta-analysis
3 One-stage meta-analysis
4 Summary
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
The heterogeneity issue
When Robin ruins the party...
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
The heterogeneity issue
Heterogeneitytread lightly!
When the effect of the intervention varies significantly fromone study to anotherIt can be attributed to clinical and/or methodologicaldiversity
Clinical: variability that arises from different populations,interventions, outcomes and follow-up timesMethodological: relates to differences in trial design andquality
Detecting quantifying and dealing with heterogeneity canbe very hard
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
The heterogeneity issue
Absence of heterogeneity
Assumes that thetrue effects of thestudies are allequal anddeviations occurbecause ofimprecision ofresultsAnalysed with thefixed-effectsmethod
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
The heterogeneity issue
Presence of heterogeneity
Assumes thatthere is variation inthe size of the trueeffect amongstudies (in additionto the imprecisionof results)Analysed withrandom-effectsmethods
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Outline
1 Meta-analysis overview
2 Two-stage meta-analysis
3 One-stage meta-analysis
4 Summary
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Challenges with two-stage meta-analysis
Heterogeneity is common and the fixed-effect model isunder fireMethods are asymptotic: accuracy improves as studiesincrease. But what if we only have a handful, as is usuallythe case?Almost all random-effects models (except ProfileLikelihood) do not take into account the uncertainty in τ̂2.Is this, practically, a problem?DerSimonian-Laird is the most common method ofanalysis, since it is easy to implement and widely available,but is it the best?
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Challenges with two-stage meta-analysis...continued
Can be difficult to organise since...outcomes likely to have been disseminated using a varietyof statistical parametersappropriate transformations to a common format requiredtedious task, requiring at least some statistical adeptness
Parametric random-effects models assume that both theeffects and errors are normally distributed. Are methodsrobust?Sometimes heterogeneity is estimated to be zero,especially when the number of studies is small. Goodnews?
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Outline
1 Meta-analysis overview
2 Two-stage meta-analysisthe MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
3 One-stage meta-analysis
4 Summary
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Organising
Data initially collected using data extraction formsA spreadsheet is the next logical step to summarise thereported study outcomes and identify missing dataSince in most cases MS Excel will be used we developedan add-in that can help with most processes involved inmeta-analysisMore useful when the need to combine differently reportedoutcomes arises
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
What it can do
Help with the data collection using pre-formattedworksheets.Its unique feature, which can be supplementary to othermeta-analysis software, is implementation of methods forcalculating effect sizes (& SEs) from different input typesFor each outcome of each study...
it identifies which methods can be usedcalculates an effect size and its standard errorselects the most precise method for each outcome
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
What it can do...continued
Creates a forest plot that summarises all the outcomes,organised by studyUses a variety of standard and advanced meta-analysismethods to calculate an overall effect
a variety of options is available for selecting whichoutcome(s) are to be meta-analysed from each study
Plots the results in a second forest plotReports a variety of heterogeneity measures, includingCochran’s Q, I2, HM
2 and τ̂2 (and its estimated confidenceinterval under the Profile Likelihood method)
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Advantages
Free (provided Microsoft Excel is available)Easy to use and time savingExtracted data from each study are easily accessible, canbe quickly edited or corrected and analysis repeatedChoice of many meta-analysis models, including someadvanced methods not currently available in other softwarepackages (e.g. Permutations, Profile Likelihood, REML)Unique forest plot that allows multiple outcomes per studyEffect sizes and standard errors can be exported for use inother meta-analysis software packages
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Installing
Latest version available from www.statanalysis.co.ukCompatible with Excel 2003, 2007 and 2010Manual provided but also described in:
Kontopantelis E and Reeves DMetaEasy: A Meta-Analysis Add-In for Microsoft ExcelJournal of Statistical Software, 30(7):1-25, 2009
Play video clip
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Outline
1 Meta-analysis overview
2 Two-stage meta-analysisthe MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
3 One-stage meta-analysis
4 Summary
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Stata implementation
MetaEasy methods implemented in Stata under:metaeff, which uses the different study input to provideeffect sizes and SEsmetaan, which meta-analyses the study effects with afixed-effect or one of five available random-effects models
To install, type in Stata:ssc install <command name>help <command name>
Described in:Kontopantelis E and Reeves Dmetaan: Random-effects meta-analysisThe Stata Journal, 10(3):395-407, 2010
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Outline
1 Meta-analysis overview
2 Two-stage meta-analysisthe MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
3 One-stage meta-analysis
4 Summary
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Many random-effects methodswhich to use?
DerSimonian-Laird (DL): Moment-based estimator of bothwithin and between-study varianceMaximum Likelihood (ML): Improves the variance estimateusing iterationRestricted Maximum Likelihood (REML): an ML variationthat uses a likelihood function calculated from atransformed set of dataProfile Likelihood (PL): A more advanced version of MLthat uses nested iterations for convergingPermutations method (PE): Simulates the distribution ofthe overall effect using the observed data
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Performance evaluationour approach
Simulated various distributions for the trueeffects:
NormalSkew-NormalUniformBimodal
Created datasets of 10,000meta-analyses for various numbers ofstudies and different degrees ofheterogeneity, for each distribution
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Performance evaluationour approach
Compared all methods in terms of:Coverage, the rate of true negatives when the overall trueeffect is zeroPower, the rate of true positives when the true overall effectis non-zeroConfidence Interval performance, a measure of how widethe (estimated around the effect) CI is, compared to its truewidth.
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
HomogeneityZero between study variance
0.75
0.80
0.85
0.90
0.95
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
zero between study varianceCoverage
0.50
0.60
0.70
0.80
0.90
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
zero between study variancePower (25th centile)
0.40
0.60
0.80
1.00
1.20
1.40
1.60
1.80
2.00
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
zero between study varianceOverall estimation performance
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Coverage performanceSmall and large heterogeneity under various distributional assumptions
0.75
0.80
0.85
0.90
0.95
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
sk=0, ku=3
H²=1.18 − I²=15% (normal distribution)Coverage
0.75
0.80
0.85
0.90
0.95
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
sk=2, ku=9
H²=1.18 − I²=15% (skew−normal distribution)Coverage
0.75
0.80
0.85
0.90
0.95
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
sk1=0, ku1=3, var1=.1, sk2=0, ku2=3, var2=.1
H=1.18 − I=15% (bimodal distribution)Coverage
0.75
0.80
0.85
0.90
0.95
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
H=1.18 − I=15% (uniform distribution)Coverage
0.75
0.80
0.85
0.90
0.95
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
sk=0, ku=3
H²=2.78 − I²=64% (normal distribution)Coverage
0.75
0.80
0.85
0.90
0.95
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
sk=2, ku=9
H²=2.78 − I²=64% (skew−normal distribution)Coverage
0.75
0.80
0.85
0.90
0.95
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
sk1=0, ku1=3, var1=.1, sk2=0, ku2=3, var2=.1
H=2.78 − I=64% (bimodal distribution)Coverage
0.75
0.80
0.85
0.90
0.95
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
H=2.78 − I=64% (uniform distribution)Coverage
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Power performanceSmall and large heterogeneity under various distributional assumptions
0.50
0.60
0.70
0.80
0.90
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
sk=0, ku=3
H²=1.18 − I²=15% (normal distribution)Power (25th centile)
0.50
0.60
0.70
0.80
0.90
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
sk=2, ku=9
H²=1.18 − I²=15% (skew−normal distribution)Power (25th centile)
0.50
0.60
0.70
0.80
0.90
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
sk1=0, ku1=3, var1=.1, sk2=0, ku2=3, var2=.1
H=1.18 − I=15% (bimodal distribution)Power (25th centile)
0.50
0.60
0.70
0.80
0.90
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
H=1.18 − I=15% (uniform distribution)Power (25th centile)
0.50
0.60
0.70
0.80
0.90
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
sk=0, ku=3
H²=2.78 − I²=64% (normal distribution)Power (25th centile)
0.50
0.60
0.70
0.80
0.90
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
sk=2, ku=9
H²=2.78 − I²=64% (skew−normal distribution)Power (25th centile)
0.50
0.60
0.70
0.80
0.90
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
sk1=0, ku1=3, var1=.1, sk2=0, ku2=3, var2=.1
H=2.78 − I=64% (bimodal distribution)Power (25th centile)
0.50
0.60
0.70
0.80
0.90
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
H=2.78 − I=64% (uniform distribution)Power (25th centile)
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
CI performanceSmall and large heterogeneity under various distributional assumptions
0.40
0.60
0.80
1.00
1.20
1.40
1.60
1.80
2.00
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
sk=0, ku=3
H²=1.18 − I²=15% (normal distribution)Confidence Interval performance
0.40
0.60
0.80
1.00
1.20
1.40
1.60
1.80
2.00
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
sk=2, ku=9
H²=1.18 − I²=15% (skew−normal distribution)Confidence Interval performance
0.40
0.60
0.80
1.00
1.20
1.40
1.60
1.80
2.00
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
sk1=0, ku1=3, var1=.1, sk2=0, ku2=3, var2=.1
H=1.18 − I=15% (bimodal distribution)Overall estimation performance (medians)
0.40
0.60
0.80
1.00
1.20
1.40
1.60
1.80
2.00
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
H=1.18 − I=15% (uniform distribution)Overall estimation performance
0.40
0.60
0.80
1.00
1.20
1.40
1.60
1.80
2.00
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
sk=0, ku=3
H²=2.78 − I²=64% (normal distribution)Confidence Interval performance
0.40
0.60
0.80
1.00
1.20
1.40
1.60
1.80
2.00
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
sk=2, ku=9
H²=2.78 − I²=64% (skew−normal distribution)Confidence Interval performance
0.40
0.60
0.80
1.00
1.20
1.40
1.60
1.80
2.00
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
sk1=0, ku1=3, var1=.1, sk2=0, ku2=3, var2=.1
H=2.78 − I=64% (bimodal distribution)Overall estimation performance (medians)
0.40
0.60
0.80
1.00
1.20
1.40
1.60
1.80
2.00
2 5 8 11 14 17 20 23 26 29 32 35number of studies
FE DL MLREML PL PE
H=2.78 − I=64% (uniform distribution)Overall estimation performance
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Coverage by methodLarge heterogeneity across various between-study variance distributions
0.50
0.55
0.60
0.65
0.70
0.75
0.80
0.85
0.90
0.95
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
Zero variance Normal Skew−normal
Bimodal Uniform
H=2.78 − I=64%FE − Coverage
0.80
0.85
0.90
0.95
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
Zero variance Normal Skew−normal
Bimodal Uniform
H=2.78 − I=64%DL − Coverage
0.70
0.75
0.80
0.85
0.90
0.95
1.00
%2 5 8 11 14 17 20 23 26 29 32 35
number of studies
Zero variance Normal Skew−normal
Bimodal Uniform
H=2.78 − I=64%ML − Coverage
0.80
0.85
0.90
0.95
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
Zero variance Normal Skew−normal
Bimodal Uniform
H=2.78 − I=64%REML − Coverage
0.80
0.85
0.90
0.95
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
Zero variance Normal Skew−normal
Bimodal Uniform
H=2.78 − I=64%PL − Coverage
0.90
0.95
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
Zero variance Normal Skew−normal
Bimodal Uniform
H=2.78 − I=64%PE − Coverage
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Power by methodLarge heterogeneity across various between-study variance distributions
0.20
0.30
0.40
0.50
0.60
0.70
0.80
0.90
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
Zero variance Normal Skew−normal
Bimodal Uniform
H=2.78 − I=64%FE − Power (25th centile)
0.10
0.20
0.30
0.40
0.50
0.60
0.70
0.80
0.90
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
Zero variance Normal Skew−normal
Bimodal Uniform
H=2.78 − I=64%DL − Power (25th centile)
0.20
0.30
0.40
0.50
0.60
0.70
0.80
0.90
1.00
%2 5 8 11 14 17 20 23 26 29 32 35
number of studies
Zero variance Normal Skew−normal
Bimodal Uniform
H=2.78 − I=64%ML − Power (25th centile)
0.10
0.20
0.30
0.40
0.50
0.60
0.70
0.80
0.90
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
Zero variance Normal Skew−normal
Bimodal Uniform
H=2.78 − I=64%REML − Power (25th centile)
0.00
0.10
0.20
0.30
0.40
0.50
0.60
0.70
0.80
0.90
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
Zero variance Normal Skew−normal
Bimodal Uniform
H=2.78 − I=64%PL − Power (25th centile)
0.10
0.20
0.30
0.40
0.50
0.60
0.70
0.80
0.90
1.00
%
2 5 8 11 14 17 20 23 26 29 32 35number of studies
Zero variance Normal Skew−normal
Bimodal Uniform
H=2.78 − I=64%PE − Power (25th centile)
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
CI performance by methodLarge heterogeneity across various between-study variance distributions
0.40
0.60
0.80
1.00
1.20
1.40
1.60
1.80
2.00
2 5 8 11 14 17 20 23 26 29 32 35number of studies
Zero variance Normal Skew−normal
Bimodal Uniform
H=2.78 − I=64%FE − Overall estimation performance
0.40
0.60
0.80
1.00
1.20
1.40
1.60
1.80
2.00
2 5 8 11 14 17 20 23 26 29 32 35number of studies
Zero variance Normal Skew−normal
Bimodal Uniform
H=2.78 − I=64%DL − Overall estimation performance
0.40
0.60
0.80
1.00
1.20
1.40
1.60
1.80
2.00
2 5 8 11 14 17 20 23 26 29 32 35number of studies
Zero variance Normal Skew−normal
Bimodal Uniform
H=2.78 − I=64%ML − Overall estimation performance
0.40
0.60
0.80
1.00
1.20
1.40
1.60
1.80
2.00
2 5 8 11 14 17 20 23 26 29 32 35number of studies
Zero variance Normal Skew−normal
Bimodal Uniform
H=2.78 − I=64%REML − Overall estimation performance
0.40
0.60
0.80
1.00
1.20
1.40
1.60
1.80
2.00
2 5 8 11 14 17 20 23 26 29 32 35number of studies
Zero variance Normal Skew−normal
Bimodal Uniform
H=2.78 − I=64%PL − Overall estimation performance
0.40
0.60
0.80
1.00
1.20
1.40
1.60
1.80
2.00
2 5 8 11 14 17 20 23 26 29 32 35number of studies
Zero variance Normal Skew−normal
Bimodal Uniform
H=2.78 − I=64%PE − Overall estimation performance
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Which method then?
Within any given method, the results were consistentacross all types of distribution shapeTherefore methods are highly robust against even severeviolations of the assumption of normalityChoose PE if the priority is an accurate Type I error rate(false positive)But low power makes it a poor choice when control of theType II error rate (false negative) is also important and itcannot be used with less than 6 studies
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Which method then?
For very small study numbers (≤5) only PL gives coverage>90% and an acccurate CIPL has a ‘reasonable’ coverage in most situations,especially for moderate and large heterogeneiry, giving itan edge over other methodsREML and DL perform similarly and better than PL onlywhen heterogeneity is low (I2 < 15%)The computational complexity of REML is not justified
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Outline
1 Meta-analysis overview
2 Two-stage meta-analysisthe MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
3 One-stage meta-analysis
4 Summary
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
Bring on the champagne?
Does not necessarily mean homogeneityMost methods use biased estimators and not uncommonto get a negative τ̂2 which is set to 0 by the modelWe identified a large percentage of cases where theestimators failed to identify existing heterogeneityIn our simulations, for 5 studies and I2 ≈ 29%:
30% of the meta-analyses were erroneously estimated tobe homogeneous under the DL method32% for REML and 48% for ML-PL
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
the MetaEasy add-inmetaeff & metaanMethods and performanceτ̂2 = 0
What does it mean?
In these cases coverage was substandard and was over10% lower than in cases where τ̂2 > 0, on averageThe problem becomes less profound as the number ofstudies and the level of heterogeneity increaseBetter estimators are neededThere might be a large number of meta-analyses of‘homogeneous’ studies which have reached a wrongconclusion
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Outline
1 Meta-analysis overview
2 Two-stage meta-analysis
3 One-stage meta-analysis
4 Summary
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Forest plot
One advantage of two-stage meta-analysis is the ability toconvey information graphically through a forest plot
study effects available after the first stage of the process,and can be used to demonstrate the relative strength of theintervention in each study and across allinformative, easy to follow and particularly useful forreaders with little or no methodological experiencekey feature of meta-analysis and always presented whentwo-stage meta-analyses are performed
In one-stage meta-analysis, only the overall effect iscalculated and creating a forest-plot is not straightforward
Enter ipdforest
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Outline
1 Meta-analysis overview
2 Two-stage meta-analysis
3 One-stage meta-analysisA practical guideipdforest methodsipdforest examplesPower
4 Summary
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
The hypothetical study
Individual patient data from randomised controlled trialsFor each trial we have
a binary control/intervention membership variablebaseline and follow-up data for the continuous outcomecovariates
Assume measurements consistent across trials andstandardisation is not requiredWe will explore linear random-effects models with thextmixed command; application to the logistic case usingxtmelogit should be straightforwardIn the models that follow, in general, we denote fixedeffects with ‘γ’s and random effects with ‘β’s
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Model 1fixed common intercept; random treatment effect; fixed effect for baseline
Yi j = γ0 + β1jgroupi j + γ2Ybi j + εi j εi j ∼ N(0, σ2j )
β1j = γ1 + u1j u1j ∼ N(0, τ12)
i : the patientj : the trialYi j : the outcomeγ0: fixed common interceptβ1j : random treatmenteffect for trial jγ1: mean treatment effectgroupi j : group membership
γ2: fixed baseline effectYbi j : baseline scoreu1j : random treatmenteffect for trial jτ1
2: between trial varianceεi j : error termσ2
j : within trial variance fortrial j
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Model 1fixed common intercept; random treatment effect; fixed effect for baseline
Possibly the simplest approachIn Stata it can be expressed as
xtmixed Y i.group Yb || studyid:group,noconswherestudyid, the trial identifiergroup, control/intervention membershipY and Yb, endpoint and baseline scoresnote that the nocons option suppresses estimation of theintercept as a random effect
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Model 2fixed trial specific intercepts; random treatment effect; fixed trial-specific effects forbaseline
Common intercept & fixed baseline difficult to justifyA more accepted model allows for different fixed interceptsand fixed baseline effects for each trial:
Yi j = γ0 j + β1 jgroupi j + γ2 jYbi j + εi jβ1 j = γ1 + u1 jwhereγ0 j the fixed intercept for trial jγ2 j the fixed baseline effect for trial j
In Stata expressed as:xtmixed Y i.group i.studyid Yb1 Yb2 Yb3 Yb4|| studyid:group, noconswhere Yb‘i’=Yb if studyid=‘i’ and zero otherwise
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Model 3random trial intercept; random treatment effect; fixed trial-specific effects for baseline
Another possibility, althought contentious, is to assume trialintercepts are random (e.g. multi-centre trial):
Yi j = β0 j + β1 jgroupi j + γ2 jYbi j + εi jβ0 j = γ0 + u0 jβ1 j = γ1 + u1 jwiser to assume random effects correlation ρ 6= 0:εi j ∼ N(0, σ2
j ) u0 j ∼ N(0, τ20 )
u1 j ∼ N(0, τ21 ) cov(u0 j ,u1 j) = ρτ0τ1
In Stata expressed as:xtmixed Y i.group Yb1 Yb2 Yb3 Yb4 ||studyid:group, cov(uns)cov(uns): allows for distinct estimation of all REvariance-covariance components
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Model 4random trial intercept; random treatment effect; random effects for baseline
The baseline could also have been modelled as arandom-effect:
Yi j = β0 j + β1 jgroupi j + β2 jYbi j + εi jβ0 j = γ0 + u0 jβ1 j = γ1 + u1 jβ2 j = γ2 + u2 jas before, non-zero random effects correlations:
u0 j ∼ N(0, τ20 ) u1 j ∼ N(0, τ2
1 )u2 j ∼ N(0, τ2
2 ) cov(u0 j ,u1 j) = ρ1τ0τ1cov(u0 j ,u2 j) = ρ2τ0τ2 cov(u1 j ,u2 j) = ρ3τ1τ2
In Stata expressed as:xtmixed Y i.group Yb || studyid:group Yb,cov(uns)
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Model 5Interactions and covariates
A covariate or an interaction term can be modelled as afixed or random effectAssuming continuous and standardised variable age wecan expand Model 2 to include fixed effects for both ageand its interaction with the treatment:
Yi j = γ0 j +β1 jgroupi j +γ2 jYbi j +γ3agei j +γ4groupi jagei j +εi jβ1 j = γ1 + u1 j
In Stata expressed as:xtmixed Y i.group i.studyid Yb1 Yb2 Yb3 Yb4age i.group#c.age || studyid:group, nocons
If modelled as a random effect, non-convergence issuesmore likely to be encountered
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Outline
1 Meta-analysis overview
2 Two-stage meta-analysis
3 One-stage meta-analysisA practical guideipdforest methodsipdforest examplesPower
4 Summary
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
General
ipdforest is issued following an IPD meta-analysis thatuses mixed effects two-level regression, with patientsnested within trials and a
linear model (xtmixed)orlogistic model (xtmelogit)
Provides a meta-analysis summary table and a forest plotTrial effects are calculated within ipdforest
Can calculate and report both main and interaction effectsOverall effect(s) and variance estimates are extracted fromthe preceding regression
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Process
ipdforest estimates individual trial effects and theirstandard errors using one-level linear or logisticregressionsFollowing xtmixed, regress is used and followingxtmelogit, logit is used, for each trialipdforest controls these regressions for fixed- orrandom-effects covariates that were specified in thepreceding two-level regressionUser has full control over included covariates in thecommand (e.g. specification as fixed- or random-effects)But we strongly recommend using the same specifications
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Estimation details
In the estimation of individual trial effects, ipdforestcontrols for a random-effects covariate (i.e. allowing theregression coefficient to vary by trial) by including thecovariate as an independent variable in each regressionControl for a fixed-effect covariate (regression coefficientassumed constant across trials and given by the coefficientestimated under two-level model) is a little more complex.
Not possible to specify a fixed value for a regressioncoefficient under regress and the continuous outcomevariable is adjusted by subtracting the contribution of thefixed covariates to its values in a first step prior to analysisFor a binary outcome the equivalent is achieved throughuse of the offset option in logit
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Reported heterogeneity
For continuous outcomes, ipdforest reports, I2 and H2M ,
based on the xtmixed outputFor binary outcomes, an estimate of the within-trialvariance is not reported under xtmelogit and henceheterogeneity measures cannot be computedBetween-trial variability estimate τ̂2 and its confidenceinterval is reported under both modelsRandom-effects model approach is more conservative,accounting for even low levels of τ2
Described in:Kontopantelis E and Reeves DA short guide and a forest plot command (ipdforest) forone-stage meta-analysisThe Stata Journal, in print
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Outline
1 Meta-analysis overview
2 Two-stage meta-analysis
3 One-stage meta-analysisA practical guideipdforest methodsipdforest examplesPower
4 Summary
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Depression intervention
We apply the ipdforest command to a dataset of 4depression intervention trialsComplete information in terms of age, gender,control/intervention group membership, continuousoutcome baseline and endpoint values for 518 patientsResults not published yet; we use fake author names andgenerated random continuous & binary outcome variables,while keeping the covariates at their actual valuesIntroduced correlation between baseline and endpointscores and between-trial variabilityLogistic IPD meta-analysis, followed by ipdforest
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Dataset
. use ipdforest_example.dta,
. describe
Contains data from ipdforest_example.dtaobs: 518vars: 17 6 Feb 2012 11:14size: 20,202
storage display valuevariable name type format label variable label
studyid byte %22.0g stid Study identifierpatid int %8.0g Patient identifiergroup byte %20.0g grplbl Intervention/control groupsex byte %10.0g sexlbl Genderage float %10.0g Age in yearsdepB byte %9.0g Binary outcome, endpointdepBbas byte %9.0g Binary outcome, baselinedepBbas1 byte %9.0g Bin outcome baseline, trial 1depBbas2 byte %9.0g Bin outcome baseline, trial 2depBbas5 byte %9.0g Bin outcome baseline, trial 5depBbas9 byte %9.0g Bin outcome baseline, trial 9depC float %9.0g Continuous outcome, endpointdepCbas float %9.0g Continuous outcome, baselinedepCbas1 float %9.0g Cont outcome baseline, trial 1depCbas2 float %9.0g Cont outcome baseline, trial 2depCbas5 float %9.0g Cont outcome baseline, trial 5depCbas9 float %9.0g Cont outcome baseline, trial 9
Sorted by: studyid patid
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
ME logistic regression model - continuous interactionfixed trial intercepts; fixed trial effects for baseline; random treatment and age effects
. xtmelogit depB group agec sex i.studyid depBbas1 depBbas2 depBbas5 depBbas9 i> .group#c.agec || studyid:group agec, var nocons or
Mixed-effects logistic regression Number of obs = 518Group variable: studyid Number of groups = 4
Obs per group: min = 42avg = 129.5max = 214
Integration points = 7 Wald chi2(11) = 42.06Log likelihood = -326.55747 Prob > chi2 = 0.0000
depB Odds Ratio Std. Err. z P>|z| [95% Conf. Interval]
group 1.840804 .3666167 3.06 0.002 1.245894 2.71978agec .9867902 .0119059 -1.10 0.270 .9637288 1.010403sex .7117592 .1540753 -1.57 0.116 .4656639 1.087912
studyid2 1.050007 .5725516 0.09 0.929 .3606166 3.0573035 .8014551 .5894511 -0.30 0.763 .189601 3.3877999 1.281413 .6886057 0.46 0.644 .4469619 3.673735
depBbas1 3.152908 1.495281 2.42 0.015 1.244587 7.987253depBbas2 4.480302 1.863908 3.60 0.000 1.982385 10.12574depBbas5 2.387336 1.722993 1.21 0.228 .5802064 9.823007depBbas9 1.881203 .7086507 1.68 0.093 .8990569 3.936262
group#c.agec1 1.011776 .0163748 0.72 0.469 .9801858 1.044385
_cons .5533714 .2398342 -1.37 0.172 .2366472 1.293993
Random-effects Parameters Estimate Std. Err. [95% Conf. Interval]
studyid: Independentvar(group) 8.86e-21 2.43e-11 0 .var(agec) 5.99e-18 4.40e-11 0 .
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
ipdforestmodelling main effect and interaction
. ipdforest group, fe(sex) re(agec) ia(agec) or
One-stage meta-analysis results using xtmelogit (ML method) and ipdforestMain effect (group)
Study Effect [95% Conf. Interval] % Weight
Hart 2005 2.118 0.942 4.765 19.88Richards 2004 2.722 1.336 5.545 30.69Silva 2008 2.690 0.748 9.676 8.11Kompany 2009 1.895 0.969 3.707 41.31
Overall effect 1.841 1.246 2.720 100.00
One-stage meta-analysis results using xtmelogit (ML method) and ipdforestInteraction effect (group x agec)
Study Effect [95% Conf. Interval] % Weight
Hart 2005 0.972 0.901 1.049 19.88Richards 2004 0.995 0.937 1.055 30.69Silva 2008 0.987 0.888 1.098 8.11Kompany 2009 1.077 1.015 1.144 41.31
Overall effect 1.012 0.980 1.044 100.00
Heterogeneity Measures
value [95% Conf. Interval]
I^2 (%) .H^2 .tau^2 est 0.000 0.000 .
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Forest plotsmain effect and interaction
Overall effect
Kompany 2009
Silva 2008
Richards 2004
Hart 2005
Stu
dies
0 2 3 4 5 6 7 8 9 101Effect sizes and CIs (ORs)
Main effect (group)
Overall effect
Kompany 2009
Silva 2008
Richards 2004
Hart 2005
Stu
dies
0 .2 .4 .6 .8 1.2 1.41Effect sizes and CIs (ORs)
Interaction effect (group x agec)
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
ME logistic regression model - binary interactionfixed trial intercepts; fixed trial effects for baseline & age cat; random treatment effect
. xtmelogit depB group i.agecat sex i.studyid depBbas1 depBbas2 depBbas5 depBba> s9 i.group#i.agecat || studyid:group, var nocons or
Mixed-effects logistic regression Number of obs = 518Group variable: studyid Number of groups = 4
Obs per group: min = 42avg = 129.5max = 214
Integration points = 7 Wald chi2(11) = 42.67Log likelihood = -326.24961 Prob > chi2 = 0.0000
depB Odds Ratio Std. Err. z P>|z| [95% Conf. Interval]
group 1.931763 .5702338 2.23 0.026 1.083151 3.4452331.agecat .7389353 .213031 -1.05 0.294 .4199616 1.300179
sex .7173044 .154959 -1.54 0.124 .469698 1.095439
studyid2 1.029638 .5608887 0.05 0.957 .3539959 2.9948235 .828577 .6082301 -0.26 0.798 .1965599 3.4927779 1.266728 .6812765 0.44 0.660 .4414556 3.634794
depBbas1 3.196139 1.515334 2.45 0.014 1.261999 8.094542depBbas2 4.625802 1.923028 3.68 0.000 2.047989 10.44832depBbas5 2.354493 1.692149 1.19 0.233 .5756364 9.630454depBbas9 1.902359 .7183054 1.70 0.089 .9075907 3.987446
group#agecat1 0 .9277371 .3558053 -0.20 0.845 .4374944 1.9673311 1 1 (omitted)
_cons .6175744 .2800575 -1.06 0.288 .253914 1.502076
Random-effects Parameters Estimate Std. Err. [95% Conf. Interval]
studyid: Identityvar(group) 2.24e-19 1.24e-10 0 .
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
ipdforestmodelling main effect and interaction
. ipdforest group, fe(sex i.agecat) ia(i.agecat) or
One-stage meta-analysis results using xtmelogit (ML method) and ipdforestMain effect (group), agecat=0
Study Effect [95% Conf. Interval] % Weight
Hart 2005 3.594 1.133 11.402 19.88Richards 2004 2.814 1.034 7.657 30.69Silva 2008 3.750 0.585 24.038 8.11Kompany 2009 1.010 0.475 2.147 41.31
Overall effect 1.792 1.079 2.976 100.00
One-stage meta-analysis results using xtmelogit (ML method) and ipdforestMain effect (group), agecat=1
Study Effect [95% Conf. Interval] % Weight
Hart 2005 1.166 0.376 3.617 19.88Richards 2004 2.566 1.007 6.543 30.69Silva 2008 1.935 0.340 11.003 8.11Kompany 2009 3.551 1.134 11.126 41.31
Overall effect 1.932 1.083 3.445 100.00
Heterogeneity Measures
value [95% Conf. Interval]
I^2 (%) .H^2 .tau^2 est 0.000 0.000 .
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Forest plotsmain effect for each age group
Overall effect
Meyer 2009
Lovell 2008
Willemse 2004
Mead 2005
Stu
dies
0 2 4 6 8 10 12 14 16 18 20 22 24 261Effect sizes and CIs (ORs)
Main effect (group), agecat=0
Overall effect
Meyer 2009
Lovell 2008
Willemse 2004
Mead 2005
Stu
dies
0 2 4 6 8 10 121Effect sizes and CIs (ORs)
Main effect (group), agecat=1
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Outline
1 Meta-analysis overview
2 Two-stage meta-analysis
3 One-stage meta-analysisA practical guideipdforest methodsipdforest examplesPower
4 Summary
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Power calculationsto detect a moderator effect
The best approach is through simulationsAs always, numerous assumptions need to be made
effect sizes (main and interaction)exposure and covariate distributionscorrelation between variableswithin-study (error) variancebetween-study (error) variance - ICC
Generate 100s of data sets using the assumed model(s)Estimate what % of these give a significant p-value for theinteractionCan be trial and error till desired power level achieved
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
A practical guideipdforest methodsipdforest examplesPower
Research on power calculations with simulationsThe Stata Journal (2002)2, Number 2, pp. 107–124
Power by simulation
A. H. FeivesonNASA Johnson Space [email protected]
Abstract. This paper describes how to write Stata programs to estimate the powerof virtually any statistical test that Stata can perform. Examples given includethe t test, Poisson regression, Cox regression, and the nonparametric rank-sumtest.
Keywords: st0010, power, simulation, random number generation, postfile, copula,sample size
1 Introduction
Statisticians know that in order to properly design a study producing experimentaldata, one needs to have some idea of whether the scope of the study is sufficient to givea reasonable expectation that hypothesized effects will be detectable over experimentalerror. Most of us have at some time used published procedures or canned softwareto obtain sample sizes for studies intended to be analyzed by t tests, or even analysisof variance. However, with more complex methods for describing and analyzing bothcontinuous and discrete data (for example, generalized linear models, survival models,selection models), possibly with provisions for random effects and robust variance es-timation, the closed-form expressions for power or for sample sizes needed to achievea certain power do not exist. Nevertheless, Stata users with moderate programmingability can write their own routines to estimate the power of virtually any statisticaltest that Stata can perform.
2 General approach to estimating power
2.1 Statistical inference
Before describing methodology for estimating power, we first define the term “power”and illustrate the quantities that can affect it. In this article, we restrict ourselvesto classical (as opposed to Bayesian) methodology for performing statistical inferenceon the effect of experimental variable(s) X on a response Y . This is accomplished bycalculating a p-value that attempts to probabilistically describe the extent to which thedata are consistent with a null hypothesis, H0, that X has no effect on Y . We wouldthen reject H0 if the p-value is less than a predesignated threshold α. It should bepointed out that considerable criticism of the use of p-values for statistical inference hasappeared in the literature; for example, Berger and Sellke (1987), Loftus (1993), andSchervish (1996). However, for this article, we accept this methodology as the modusoperandi.
c© 2002 Stata Corporation st0010
COMMENTARY Open Access
Simulation methods to estimate design power:an overview for applied researchBenjamin F Arnold1*†, Daniel R Hogan2†, John M Colford Jr1 and Alan E Hubbard3
Abstract
Background: Estimating the required sample size and statistical power for a study is an integral part of studydesign. For standard designs, power equations provide an efficient solution to the problem, but they areunavailable for many complex study designs that arise in practice. For such complex study designs, computersimulation is a useful alternative for estimating study power. Although this approach is well known amongstatisticians, in our experience many epidemiologists and social scientists are unfamiliar with the technique. Thisarticle aims to address this knowledge gap.
Methods: We review an approach to estimate study power for individual- or cluster-randomized designs usingcomputer simulation. This flexible approach arises naturally from the model used to derive conventional powerequations, but extends those methods to accommodate arbitrarily complex designs. The method is universallyapplicable to a broad range of designs and outcomes, and we present the material in a way that is approachablefor quantitative, applied researchers. We illustrate the method using two examples (one simple, one complex)based on sanitation and nutritional interventions to improve child growth.
Results: We first show how simulation reproduces conventional power estimates for simple randomized designsover a broad range of sample scenarios to familiarize the reader with the approach. We then demonstrate how toextend the simulation approach to more complex designs. Finally, we discuss extensions to the examples in thearticle, and provide computer code to efficiently run the example simulations in both R and Stata.
Conclusions: Simulation methods offer a flexible option to estimate statistical power for standard and non-traditional study designs and parameters of interest. The approach we have described is universally applicable forevaluating study designs used in epidemiologic and social science research.
Keywords: Computer Simulation, Power, Research Design, Sample Size
BackgroundEstimating the sample size and statistical power for astudy is an integral part of study design and has profoundconsequences for the cost and statistical precision of astudy. There exist analytic (closed-form) power equationsfor simple designs such as parallel randomized trials withtreatment assigned at the individual level or cluster(group) level [1]. Statisticians have also derived equationsto estimate power for more complex designs, such asdesigns with two levels of correlation [2] or designs withtwo levels of correlation, multiple treatments and
attrition [3]. The advantage of using an equation to esti-mate power for study designs is that the approach is fastand easy to implement using existing software. For thisreason, power equations are used to inform most studydesigns. However, in our applied research we have routi-nely encountered study designs that do not conform toconventional power equations (e.g. multiple treatmentinterventions, where one treatment is deployed at thegroup level and a second at the individual level). In thesesituations, simulation techniques offer a flexible alterna-tive that is easy to implement in modern statisticalsoftware.Here, we provide an overview of a general method to
estimate study power for randomized trials based on asimulation technique that arises naturally from the
* Correspondence: [email protected]† Contributed equally1Division of Epidemiology, School of Public Health, University of California,Berkeley, CA, USAFull list of author information is available at the end of the article
Arnold et al. BMC Medical Research Methodology 2011, 11:94http://www.biomedcentral.com/1471-2288/11/94
© 2011 Arnold et al; licensee BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative CommonsAttribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction inany medium, provided the original work is properly cited.
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
Outline
1 Meta-analysis overview
2 Two-stage meta-analysis
3 One-stage meta-analysis
4 Summary
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
Two-stage meta-analysis
MetaEasy can help you organise your meta-analysis andcan be especially useful if you need to combine continuousand binary outcome.Methods implemented in Stata under metaeff and metaanA zero τ̂2 is a reason to worry; heterogeneity might bethere but we cannot measure or account for in the modelIf τ̂2 > 0, even if very small, use a random-effects modelThe DL method works reasonably well, under alldistributions, especially for low levels of heterogeneityProfile likelihood, which takes into account the uncertaintlyin τ̂2, works better when I2 ≥ 15%
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
Meta-analysis overviewTwo-stage meta-analysisOne-stage meta-analysis
Summary
One-stage meta-analysis
A few different approaches exist for conducting one-stageIPD meta-analysisStata can cope through the xtmixed and the xtmelogitcommandsThe ipdforest command aims to help meta-analysts
calculate trial effectsdisplay results in standard meta-analysis tablesproduce familiar and ‘expected’ forest-plots
The easiest way to calculate power to detect complexeffects is through simulations
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
AppendixThank you!Key references
Comments, suggestions:[email protected]
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
Heal
th S
cien
ces P
rimar
y Ca
re R
esea
rch
Grou
p
[Poster title]
ABSTRACT TITLE: [Add text here.]
BACKGROUND: [Add text here.]
OBJECTIVE: [Add text here.]
METHODS: [Add text here.]
RESULTS: [Add text here.]
CONCLUSIONS: [Add text here.]
BACKGROUND [Add title, if necessary.]
Label One
Label Two
Label Three
Label Four
[Replace the following names and titles with those of the actual contributors: Helge Hoeing, PhD1; Carol Philips, PhD2; Jonathan Haas, RN, BSN, MHA3, and Kimberly B. Zimmerman, MD4 1[Add affiliation for first contributor], 2[Add affiliation for second contributor], 3[Add affiliation for third contributor], 4[Add affiliation for fourth contributor]
OBJECTIVE
[Repeat objective from above.]
METHODS
[Add title, if necessary.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add key point.] [Add description of key point.]
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
RESULTS
[Add title, if necessary.]
[Add key point.] [Add key point.] [Add key point.] [Add key point.] [Add key point.]
CONCLUSIONS
[Add text as bulleted list or a paragraph.] [Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Add key point.]
[Graphic title]
RESULTS
[Graphic title] [Graphic title]
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
0% 20% 40% 60% 80% 100%
1st Qtr
2nd Qtr
3rd Qtr
4th Qtr
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.]
[Replace, move, resize, or delete graphic, as necessary.] [Replace, move, resize, or delete graphic, as necessary.]
For additional information please contact: [Name] [Department] [Institution or organization] [E-mail address]
Excepteur Sint Lkl
(n=212) Controls
(n=27)
Lorum Wt (kg) 18 (SD 10) 29 (SD 07)
Ipsum (wk) 31 (SD 5) 37 (SD 2)
Irure: B W H HB O
Unknown
79 (373%) 121 (571%)
2 (09%) 0
1 (05%) 9 (42%)
7 (259%) 18 (667%)
0 1 (37%) 1 (37%)
0
Proident F
Lorem
106 (50%) 101 (476%)
5 (24%)
17 (63%) 10 (37%)
Nostrud: N Y
Unknown
172 (811%) 22 (104%) 18 (85%)
26 (963%) 0
1 (37%)
[Add title, if necessary.]
[Add key point.] [Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add title, if necessary.]
[Add key point.]
[Sub-bullet] [Sub-bullet]
[Add key point.]
[Sub-bullet] [Sub-bullet]
AppendixThank you!Key references
References
Kontopantelis E, Reeves D.A short guide and a forest plot command (ipdforest) for one-stagemeta-analysis.The Stata Journal, in print.
Kontopantelis E, Reeves D.Performance of statistical methods for meta-analysis when true studyeffects are non-normally distributed: A simulation study.Stat Methods Med Res, published online Dec 9 2010.
Kontopantelis E, Reeves D.metaan: Random-effects meta-analysis.The Stata Journal, 10(3):395-407, 2010.
Kontopantelis E, Reeves D.MetaEasy: A Meta-Analysis Add-In for Microsoft Excel.Journal of Statistical Software, 30(7):1-25, 2009.
Kontopantelis, Reeves Software and model selection challenges in meta-analysis
