43
Statistical Reporting Stats in the literature

Statistical Reporting Stats in the literature

  • Upload
    tamera

  • View
    19

  • Download
    0

Embed Size (px)

DESCRIPTION

Statistical Reporting Stats in the literature. Tables, Graphs, Words ( van Belle-Stat rules of Thumb,2002). Bad – The blood types of the US population are 40%, 11%, 4% and 45% for A, B, AB and O respectively. Good - Blood type percent O 45% - PowerPoint PPT Presentation

Citation preview

Page 1: Statistical Reporting Stats in the literature

Statistical ReportingStats in the literature

Page 2: Statistical Reporting Stats in the literature

2

Tables, Graphs, Words (van Belle-Stat rules of Thumb,2002)

Bad – The blood types of the US population are 40%, 11%, 4% and 45% for A, B, AB and O respectively.

Good- Blood type percent

O 45%

A 40%

B 11%

AB 4%

Page 3: Statistical Reporting Stats in the literature

3

Sort by frequency Occupation active in 1980 - bad

Chiropractors 25,600

Dentists 121,240

Nutritionists 32,000

Nurses 1,272,900

Optometrists 22,330

Pharmacists 142,780

Physicians 427,122

Page 4: Statistical Reporting Stats in the literature

4

Good

Occupation active in 1980

Nurses 1,272,900

Physicians 427,122

Pharmacists 142,780

Dentists 121,240

Nutritionists 32,000

Chiropractors 25,600

Optometrists 22,330

Page 5: Statistical Reporting Stats in the literature

5

Don’t use pie charts(particularly for 2+ dimensions)

Page 6: Statistical Reporting Stats in the literature

6

Use sorted tables

Blood type Rh + Rh- total

O 38 7 45

A 34 6 40

B 9 2 11

AB 3 1 4

total 84 16 100

Page 7: Statistical Reporting Stats in the literature

7

Bar graphs ok in simple situations(& put in SE or CI bars)

Page 8: Statistical Reporting Stats in the literature

8

Don’t use bar graphs in complex situations

Page 9: Statistical Reporting Stats in the literature

9

Use line graph

Page 10: Statistical Reporting Stats in the literature

10

Try not to use asterisks to report p values

* = 0.05 ≤ p < 0.10

** = 0.01 ≤ p < 0.05

*** = p < 0.01

Page 11: Statistical Reporting Stats in the literature

11

***

Page 12: Statistical Reporting Stats in the literature

12

Report actual p valuesBe clear about the reference group

*p value compared to control group

report actual p values when possible, not just an asterisk if p < 0.05. (Tables better than bar

charts for this).

group n mean SEM p value*

cntl 12 20 5 ref

B 22 35 6 0.062

C 9 50 5 0.020

D 7 15 4 0.124

Page 13: Statistical Reporting Stats in the literature

13

Don’t cut off axis too high

Page 14: Statistical Reporting Stats in the literature

Misc rules (Petrie & Sabin)Don’t use 3-D bars for one variable. Report n. Report SE or CI for all estimatesMake sure all estimates are labeled with the

correct units (ie b=3.0 mg/L, not b=3.0)Define any uncommon symbols, including

those for equations. (b=slope, Δ=mean difference in mg). Define abbreviations.

Make sure all tables have a title.Label all axes & bars and explain the

meaning of all graph symbols.

Page 15: Statistical Reporting Stats in the literature

Misc rules (cont.)

Be careful about drawing firm conclusions about issues on which no data were presented. Distinguish between conclusions vs discussion/speculation.

Enough info should be given so results could be reproduced by a person with the proper training if raw data was provided.

Page 16: Statistical Reporting Stats in the literature

16

Reporting GuidelinesCONSORT (CONsolidated Standards for

Reporting Trials) guidelines are formulated for clinical trials-but most of the guidelines apply to other designs.

STROBE (STrengthening the Reporting of OBservational studies in Epi) statement.

TRIPOD (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis

Page 17: Statistical Reporting Stats in the literature

17

From CONSORT checklist

*Objectives & hypotheses

*Background & rationale

*Design, inclusion/exclusion criteria

*Settings (population) & locations where data collected

*Blinding (if relevant)

*Interventions (if any)

*Primary & secondary outcomes

Page 18: Statistical Reporting Stats in the literature

18

Example: diet studyObjective- Compare wt loss under 4 dietsDesign – RCT, twelve month trialSetting & Participants – local recruitment. Trial

conducted in US from Feb 2003 to Oct 2005 among 311 free-living, overweight/obese (BMI 27-40) nondiabetic, premenopausal women.

Blinding – Not possible for patientsInterventions – 4 dietsPrimary outcome – 12 month wt lossSecondary outcomes – Lipids (LDL,HCL), insulin,

glucose, BP, energy, carbs, protein

Page 19: Statistical Reporting Stats in the literature

19

Statistical checklist *How sample size was determined-power

*How randomization was done, if relevant

(Blocks, stratified?)

*Interim analysis & stopping rules, if any.

*Statistical methods used-tests (parametric or non), models, univariate & multivariate methods, multiple testing correction method (if any), assumptions

Page 20: Statistical Reporting Stats in the literature

20

Diet study –sample sizeSample size –”Based on previous trials,

we projected a 6.3-kg SD of weight change….Thus, with 4 treatment groups and a projected 75 participants per group, the study was designed to have 80% power to detect a 2.7 kg difference for the 12 month weight change between groups.”

Page 21: Statistical Reporting Stats in the literature

21

Diet study – sample size

σ = 6.3 kg α = 0.05, Z0.975=1.96

Δ = 2.7 kg power = 0.80, Z0.800=0.84

n = 2(Zα + Zpower)2(σ/Δ)2

= 2(1.96 + 0.84)2 (σ/Δ)2

n = (15.7)(6.3/2.7)2 = 85 ???

(ANOVA correction, k=4, gives n=81)

Page 22: Statistical Reporting Stats in the literature

22

Diet Study- Randomization

Randomization – “Randomization was conducted in blocks of 24 (6 per treatment group) and occurred by having a blinded research technician select folded pieces of paper with group assignments from an opaque envelope”.

Page 23: Statistical Reporting Stats in the literature

23

Diet Study- stat methodsStatistical Methods - Differences among

diets for 12-month changes from baseline were tested by ANOVA. For statistically significant ANOVAs, all pairwise comparisons among the 4 diets were tested using the Tukey studentized range adjustment. Statistical testing of changes from baseline to 2 months and to 6 months using pairwise comparisons are presented for descriptive purposes.

Page 24: Statistical Reporting Stats in the literature

24

Diet study – stat methods

Multiple regression was used to examine potential interactions between race/ethnicity and diet group for effects on weight loss; there were no significant interactions. All statistical tests were 2-tailed using a significance level of 0.05.

Page 25: Statistical Reporting Stats in the literature

25

Reporting:

Number analyzed, lost/missing, excluded

Baseline data including demographics

Stats for primary outcome at least!

Absolute and relative measures for binary outcomes

Discussion:

Limitations, generalisability, biases, was power/sample size adequate?

Sources of funding, acknowledgements

Page 26: Statistical Reporting Stats in the literature

26

Page 27: Statistical Reporting Stats in the literature

27

Page 28: Statistical Reporting Stats in the literature

28

Diet study-baseline

Page 29: Statistical Reporting Stats in the literature

29

Diet study- Primary outcome

Atkins is best

Page 30: Statistical Reporting Stats in the literature

30

Diet study- limitations

Insufficient follow up – wt still increasing

No assessment of diet adherence

Prior exposure to diet before study

No assessment of satiety

Menstural cycle not considered when measuring lipids

Page 31: Statistical Reporting Stats in the literature

31

Good organization – Put the statistical methods in a subsection of the methods section.

Don’t need to repeat statistical methods in the results section, don’t put methods in results section or results in the methods section.

Try to use the same order of presentation in all sections.

Page 32: Statistical Reporting Stats in the literature

32

Example:Statistical methods: Means +/- SEM in ml are

reported for sperm volume.

The p values for comparing mean sperm volume across groups were computed under an analysis of variance (ANOVA) model. The Fisher LSD criterion was used to control for multiple comparisons.

Quantile plots were examined to see if sperm volume followed the Gaussian distribution.

Page 33: Statistical Reporting Stats in the literature

33

(methods):

The p values for comparing proportions were computed using chi-square tests.

Multivariate-

Linear regression was used to quantify the association of sperm volume with age and occupation. Spline methods were used to verify that the relationship was linear.

A p < 0.05 is considered statistically significant.

Page 34: Statistical Reporting Stats in the literature

34

Results:

Table 1 shows that the mean sperm volume was highest in the biostatistics group and was significantly higher than controls (5.0+/- 1.0 vs 3.2+/-0.9, p = 0.0274).

Figure 1 shows sperm volume versus age in controls. The average rate of decline was 0.30 +/- 0.07 ml/year.

Page 35: Statistical Reporting Stats in the literature

35

Mistakes that make me suspicious*If there are “n” rats in your study, do the

various sample size tables add up to “n”?

*Is the amount of missing reported?

*Do numbers add up?

*If the mean in group A is 20 and the mean in group B is 40, and these are the only groups, is the overall mean between 20 and 40?

*If mean time from v1 to v2 is 4 mos & from v2 to v3 is 1 month, is time from v1 to v3=5 mos?

Page 36: Statistical Reporting Stats in the literature

36

*Do SDs imply that the 95% PI takes impossible values (negative)?

(need a transformation?)*Are correlations, ORs, RRs, in impossible

directions?*Are p values reported with NO summary

statistics? (gender was sig, p < 0.01)* Are SEs or CIs reported, labeled with

correct units & not confused with SDs or PIs?

Page 37: Statistical Reporting Stats in the literature

SurvivalAre survival curves and/or hazard rates

reported (with SEs), not just percent alive with no time info attached?

Want statistics for follow up time including median (not mean) follow up time. Same follow up in each group?

Should not extend survival curve to last follow up time, when most are dead and/or have no follow up.

Page 38: Statistical Reporting Stats in the literature

38

Multivariate regression (TRIPOD):

What were the candidate predictors?

What method was used to pick the final predictors (ex:what α level was used?)

Were interactions considered at least with the primary predictor of interest (jg) ?

Was linearity assumed or verified?(JG-Final equation given in an appendix or footnote?)

SEs or CIs given for all βs or their transformation (ORs, HRs)?

Were performance/fit measures reported?

Was there validation?

Page 39: Statistical Reporting Stats in the literature

Regression results are in tables Predictors of in hospital infection Characteristic Odds Ratio (95% CI) p value Incr APACHE score 1.15 (1.11-1.18) <.001 Transfusion (y/n) 4.15 (2.46-6.99) <.001 Increasing age 1.03 (1.02-1.05) <.001 Malignancy 2.60 (1.62-4.17) <.001 Max Temperature 0.70 (0.58-0.85) <.001 Adm to treat>7 d 1.66 (1.05-2.61) 0.03 Female (y/n) 1.32 (0.90-1.94) 0.16 *APACHE = Acute Physiology & Chronic Health Evaluation Score

Page 40: Statistical Reporting Stats in the literature

40

Abstracts vs manuscriptsBad (but common) practice to “rush” to get

abstract in before a deadline with idea that sloppy methods and results will be “fixed” in manuscript. I conclude therefore that many abstracts are not to be trusted.

Are there results in the Abstract that are not in the text?

“Never enough time to do it right, always enough time to do it over.”

Page 41: Statistical Reporting Stats in the literature

41

Science Citation index (Thomson Reuters)

Scopus (Elsevier)

“Bibliometrics” from these sources

imply that perhaps 1/3 to 1/2 of all science papers are never cited or are only cited once. This implies that, at least in part, there is a LOT of sloppy stuff in the literature that is not useful. This cluttering may actually obscure the truth.

Page 42: Statistical Reporting Stats in the literature

42

Publication bias

Negative results often not reported

Ethical issues/conflict of interest – Financial disclosure and incentives. A problem when private industry funds studies. Investigators funded by the sponsors of a treatment are more likely to give a positive report.

Page 43: Statistical Reporting Stats in the literature

43

When doing research, try to follow the advice of Mark Twain

“Always tell the truth. This will gratify some people and astonish the rest”.