Upload
janel-adams
View
216
Download
1
Embed Size (px)
DESCRIPTION
York Psychology Department Colloquium, 9 November review of articles in psychology reporting mediation analysis: N = 291 distribution across areas of psychology 34% social 24% clinical 10% health remainder in developmental I/O cognitive methods program evaluation
Citation preview
The State of Mediation Analysis in Psychological ScienceIssues and SolutionsRick HoyleDuke University
York Psychology Department Colloquium, 9 November 2015 2
putativecause
explanatorymechanism
(behavioral)outcome
York Psychology Department Colloquium, 9 November 2015 3
2006 review of articles in psychology reporting mediation analysis:
• N = 291• distribution across areas of psychology• 34% social• 24% clinical• 10% health• remainder in• developmental• I/O• cognitive• methods• program evaluation
York Psychology Department Colloquium, 9 November 2015 4
York Psychology Department Colloquium, 9 November 2015 5
review of social psychology articles published from 2005-2009:
• at least one mediation test• 59% of articles in JPSP• 65% of articles in PSPB
York Psychology Department Colloquium, 9 November 2015 6
JPSP (latest issue)
York Psychology Department Colloquium, 9 November 2015 7
JCCP (latest issue)
York Psychology Department Colloquium, 9 November 2015 8
Psych Science (latest issue)
York Psychology Department Colloquium, 9 November 2015 9
JEP: General (latest issue)
York Psychology Department Colloquium, 9 November 2015 10
York Psychology Department Colloquium, 9 November 2015 11
York Psychology Department Colloquium, 9 November 2015 12
York Psychology Department Colloquium, 9 November 2015 13
Origins and Early Developments
York Psychology Department Colloquium, 9 November 2015 14
counter-attitudina
l statemen
t
cognitivedissonance
attitudechange
social psychologists, in particular, have long theorized about and drawn inferences with reference to mediators without directly observing them or accounting for them in hypothesis tests
York Psychology Department Colloquium, 9 November 2015 15
counter-attitudina
l statemen
t
cognitivedissonance
attitudechange
self-imagethreat
self-perception
self-inconsistency
York Psychology Department Colloquium, 9 November 2015 16
“When what a person does [is] attributed to what is going on inside him, investigation is brought to an end.” (Skinner, 1974)
York Psychology Department Colloquium, 9 November 2015 17
“The time seems to have come when psychology must discard all reference to consciousness; when it need no longer delude itself into thinking that it is making mental states the object of observation.”
Watson (1913), “Psychology as the Behaviorist Views It”vs.
“Who can possibly care about a psychology that is silent on such topics as thinking, motivation, and volition?”
Kimble (1989), “Psychology from the Standpoint of a Generalist”
York Psychology Department Colloquium, 9 November 2015 18
“First psychology lost its soul, then it lost its mind, then it lost consciousness; it still has behavior, of a kind.”“In order to predict the response, we must know not only the stimulus, but also the organism stimulated”“Behavior we can observe, consciousness we can observe with some difficulty, but the inner dynamics of the mental processes must be inferred rather than observed. . . . A dynamic psychology must utilize the observations of consciousness and behavior as indications of the 'workings of the mind' . . . ”Woodworth (1918), Dynamic Psychology
York Psychology Department Colloquium, 9 November 2015 19
Tolman’s (1938) intervening variable framework
“Some of us, psychologically, just demand theories. Even if we had all the million and one concrete facts, we would still want theories to, as we would say, “explain” those facts. Theories just seem to be necessary to some of us to relieve our inner tensions.”“A theory, as I shall conceive it, is a set of “intervening variables.” These to-be-inserted variables are “constructs” which we, the theorists, evolve . . . .”
York Psychology Department Colloquium, 9 November 2015 20
“Mentalistic concepts enter psychology as inferences from behavior. The observations that define them often suggest causes.” (Kimble, 1989)
York Psychology Department Colloquium, 9 November 2015 21
Hyman (1955)
Step 1: establish simple relationship between two variables
Step 2: introduce additional variables to address problems of spuriousness
Step 3: engage in process of elaboration; within general schema of elaboration interpret the relationship“When the analyst interprets a relationship, he [or she] determines the process through which the assumed cause is related to what we take to be its effect. . . . What are the “links” between the two variables?”
York Psychology Department Colloquium, 9 November 2015 22
two challenges for informative mediation analyses:
1. estimation and testing2. inference and interpretation
York Psychology Department Colloquium, 9 November 2015 23
Statistical Tests
York Psychology Department Colloquium, 9 November 2015 24
X
M
Yc'
a b
York Psychology Department Colloquium, 9 November 2015 25
X
M
Yc'
a b
X Yc
difference in coefficients methodc - c' > 0
York Psychology Department Colloquium, 9 November 2015 26
X
M
Yc'
a b
joint significance methoda > 0 and b > 0
York Psychology Department Colloquium, 9 November 2015 27
X
M
Yc'
a b
product of coefficients methodab > 0
York Psychology Department Colloquium, 9 November 2015 28
issue with product of coefficients method:
• problem: which standard error to use to construct the test statistic; which reference distribution for tests of significance
• test-statistic options:• Sobel approximation; normal distribution• empirical distribution of ab; tabled critical
values based on empirical distributions for different values of a and b
• distribution of product of two normal variables (zazb); critical values (or confidence interval) based on distribution of product of random variables
York Psychology Department Colloquium, 9 November 2015 29
issue with product of coefficients method:
• problem: which standard error to use to construct the test statistic; which reference distribution to test for significance
• resampling/simulation options:• percentile bootstrap confidence interval• bias corrected bootstrap• Monte Carlo simulation
York Psychology Department Colloquium, 9 November 2015 30
issue with product of coefficients method:
• problem: which standard error to use to construct the test statistic; which reference distribution to test for significance
• solutions:• test statistic: best option for power and
Type 1 error is empirical distribution of ab• resampling: percentile bootstrap if Type 1
error is primary consideration; bias corrected bootstrap if power is primary consideration
York Psychology Department Colloquium, 9 November 2015 31
Inference and Interpretation
York Psychology Department Colloquium, 9 November 2015 32
“If the mediational model is wrong (i.e., misspecified), the results from a mediational analysis are not so much meaningless, but rather they are misleading” (Kenny, 2008)Inferences about mediation are causal inferences.
1. The cause (X) precedes the mediator (M) in time, and M precedes the effect (Y) in time (i.e., temporal precedence).
2. In each case, the cause and effect are related to one another (i.e., covariation).
3. There are no rival explanations of the observed relations between the causes and effects (i.e., absence of confounds).
York Psychology Department Colloquium, 9 November 2015 33
evaluation of approaches to explicit testing of mediation hypotheses:
findings are . . .• misleading• uninformative• informative• definitive
current
desired
York Psychology Department Colloquium, 9 November 2015 34
X
M
Yc'
a b
York Psychology Department Colloquium, 9 November 2015 35
necessary for informative/definitive findings:
• temporal precedence • covariation• absence of confounds
strategies and solutions• if experimental method is feasible• randomize to levels of a manipulated X• measure or observe Y at a process-
informed interval following X
York Psychology Department Colloquium, 9 November 2015 36
necessary for informative/definitive findings:
• temporal precedence • covariation• absence of confounds
strategies and solutions• if randomization to levels of a manipulated X
isn’t feasible or successful• use statistical means to isolate X by
including covariates in the model
York Psychology Department Colloquium, 9 November 2015 37
X
M
Yc'
a b
Ci
C1
...
York Psychology Department Colloquium, 9 November 2015 38
necessary for informative/definitive findings:
• temporal precedence • covariation• absence of confounds
strategies and solutions• if X is not manipulated• longitudinal design to address temporal
order• inclusion of covariates to achieve some
measure of isolation of X
York Psychology Department Colloquium, 9 November 2015 39
the problem of equivalent models in data from nonexperimental studies
X Y
X Y
X Y
X Y
C1.
2.
3.
4.
York Psychology Department Colloquium, 9 November 2015 40
X
M
Yc'
a b
York Psychology Department Colloquium, 9 November 2015 41
necessary for informative/definitive findings:
• temporal precedence • covariation• absence of confounds
strategies and solutions• if experimental method is feasible• randomize to levels of a manipulated X• measure or observe M at a process-
informed interval following X
York Psychology Department Colloquium, 9 November 2015 42
necessary for informative/definitive findings:
• temporal precedence • covariation• absence of confounds
strategies and solutions• if manipulation is not possible• longitudinal design to address temporal
order• inclusion of covariates to achieve some
measure of isolation of X
York Psychology Department Colloquium, 9 November 2015 43
X
M
Yc'
a b
Ci
C1
...
York Psychology Department Colloquium, 9 November 2015 44
X
M
Yc'
a b
York Psychology Department Colloquium, 9 November 2015 45
necessary for informative/definitive findings:
• temporal precedence • covariation• absence of confounds
strategies and solutions• manipulation of M is not possible• longitudinal design to address temporal
order• inclusion of covariates to achieve some
measure of isolation of M
York Psychology Department Colloquium, 9 November 2015 46
X
M
Yc'
a b
Ci
C1
...
York Psychology Department Colloquium, 9 November 2015 47
critical issue for informative/definitive M-Y inference—and X-M inference in nonexperimental data—is temporal orderinability to draw firm directional inferences leaves open the possibility that other equivalent models provide an equally compelling account of the dataequivalent models: two or more models that, because they offer statistically equivalent accounts of the data, cannot be distinguished on statistical grounds
York Psychology Department Colloquium, 9 November 2015 48
York Psychology Department Colloquium, 9 November 2015 49
X Y
M
X Y
M
X Y
M
X Y
M
X Y
M
X Y
M
X Y
M
X Y
M
X Y
M
X Y
M
X Y
M
X Y
M
1.
2. 3.
4.
5. 6.
7.
8. 9.
10.
11.
12.
.23 .36
.26
.11 .42
.30
.10 .39
.34
.23 .42
.26
.23 .36
.26
.23 .36
.26
.12 .39
.30
.10 .39
.34
.10 .39
.34
.12 .30
.39
.11 .42
.30
.11 .42
.30
York Psychology Department Colloquium, 9 November 2015 50
“. . . that fact that a study’s results are consistent with an assumed mediation model does not allow for any valid conclusion about the correctness of the model, unless the results stem from a study that allows for ruling out rival models.” (Stone-Romero & Raposa, 2008)
York Psychology Department Colloquium, 9 November 2015 51
X1
a
b
M2
Y3
York Psychology Department Colloquium, 9 November 2015 52
X1
a
b
M1 M2
Y2 Y3
b
York Psychology Department Colloquium, 9 November 2015 53
X1
a
b
M1
Y1
X2
M2
Y2
X3
M3
Y3
b
a
York Psychology Department Colloquium, 9 November 2015 54
X1
a
b
M1
Y1
X2
M2
Y2
X3
M3
Y3
a
b
York Psychology Department Colloquium, 9 November 2015 55
X1
a
b
M1
Y1
X2
M2
Y2
X3
M3
Y3
X-M M-Y
a
b
Covariates1 Covariates2
York Psychology Department Colloquium, 9 November 2015 56
Xa
b
M2
Y2
M3
Y3
X-M M-Y
Covariates1 Covariates2
York Psychology Department Colloquium, 9 November 2015 57
issues with inferences about the extent of mediation:
• problem: under certain conditions the simple direct effect (c) might not be significant when the indirect effect (ab) is significant
• solution: focus testing and inference on the indirect effect in the full model; avoid extent of mediation inference
York Psychology Department Colloquium, 9 November 2015 58
issues with inferences about the extent of mediation:
• problem: c' may be nonsignificant but mediation not full
• solution: under certain conditions, proportion of full effect that is attributable to the indirect effect can be informative• standardized c (rxy in simple mediation
model) should be at least |.20|• proportion of effect that is through the
mediator
or
• this value is descriptive (i.e., not subject to formal inference)
cab/ cc1 /'
York Psychology Department Colloquium, 9 November 2015 59
issues with inferences about the extent of mediation:
• problem: when there is measurement error in the mediator, c' might be significant despite full mediation
• solutions: (1) use highly reliable measure of the mediator; (2) obtain multiple measures of the mediator and model it as a latent variable
brb MMobs '
')( ' cabr1c MM
York Psychology Department Colloquium, 9 November 2015 60
proposals for tests of mediation going forward:
• they should not be done unless the results will be informative (i.e., criterion is not statistical significance)
• they should not be required for circumspect, theory-driven inferences about causal mechanisms
• when they are done, they should be done better!• randomization and manipulation when
possible• careful and thorough accounting for
confounds• consideration for time passage between
assessment of variables in the causal sequence
• use of longitudinal designs appropriate for observing the focal causal sequence
York Psychology Department Colloquium, 9 November 2015 61
Pek, J., & Hoyle, R. H. (in press). On the (in)validity of tests of simple mediation: Threats and solutions. Social and Personality Psychology Compass.
Thank you!