Moderator analyses: Categorical models and Meta-regression

51
The Campbell Collaboration www.campbellcollaboration.org Moderator analyses: Categorical models and Meta- regression Terri Pigott, C2 Methods Editor & co-Chair Professor, Loyola University Chicago [email protected]

description

Moderator analyses: Categorical models and Meta-regression. Terri Pigott, C2 Methods Editor & co-Chair Professor, Loyola University Chicago [email protected]. Moderator analyses in meta-analysis. - PowerPoint PPT Presentation

Transcript of Moderator analyses: Categorical models and Meta-regression

Page 1: Moderator analyses:  Categorical models and Meta-regression

The Campbell Collaboration www.campbellcollaboration.org

Moderator analyses: Categorical models and Meta-regression

Terri Pigott, C2 Methods Editor & co-ChairProfessor, Loyola University Chicago

[email protected]

Page 2: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Moderator analyses in meta-analysis

• We often want to test our hypotheses about whether variation among studies in effect size is associated with differences in study methods or participants

• We have these ideas a priori, incorporating these characteristics of studies into our coding forms

• Two major forms of moderator analyses in meta-analysis: categorical models analogous to ANOVA, and meta-regression

Page 3: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Assumptions for this session• We will focus on random effects models as these are the

most common in Campbell reviews• I will assume that we have computed the random effects

variance component (as you did if you were in my session yesterday - though you may feel like this right now)

• We will use two software packages:– RevMan – available here:

http://ims.cochrane.org/revman/download– Comprehensive Meta-analysis – available for free download

and limited trial here: http://www.meta-analysis.com/pages/demo.html

Page 4: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Categorical moderators

• When the moderator variable is categorical, we can estimate models analogous to ANOVA

• Typically, we are interested in comparing the group mean effect sizes for 2 or more groups

• For example, we will look at a meta-analysis where we compare the mean effect size for studies published in three different sources: journals, dissertations, and unpublished studies

Page 5: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Categorical moderator models

• With a one-way random effects ANOVA model, recall that we will compute– A mean effect size and standard error for each group, and then

test whether these means are significantly different from one another

– The mean effect size and standard error require an estimate of the variance component

– QUESTION: Will we assume that each group has the same variance component? Or, will we assume that each group has its own variance component?

Page 6: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

What are our assumptions if we decide to use separate estimates within subgroups?• We believe that the variation among studies is different

between groups.• For example, if we are testing out an intervention and we

have studies that use either a low-income and a high-income group of students, we might believe that there will be more variation in effectiveness among studies that have mostly low-income participants

• Another example: the effectiveness of an intervention for juvenile delinquents will vary more for the group that had a prior arrest than for those that do not have a prior arrest

Page 7: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

What are our assumptions when we use a pooled estimate?• We believe that the variation among effect sizes are the

same no matter the group.• For an intervention review, we may assume that the variation

among studies does not differ within the groups of interest• Caveat: We might have to use a pooled estimate if we have

small sample sizes within subgroups. We need at least 5 cases (in general) to be able to estimate a separate variance component for each subgroup

Page 8: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Flowchart from Borenstein

Page 9: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Steps for a random effects ANOVA

• Make a decision about the use of a pooled or a separate estimate of the variance component

• Compute the group mean effect sizes, and their standard errors

• Compare the group mean effect sizes to see if they are statistically different from one another

Page 10: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Eagly, Johannesen-Schmidt & van Engen (2003)

• This synthesis examines the standardized mean difference estimated in primary studies for the difference between men and women in their use of transformational leadership.

• Transformational leadership involves “establishing onself as a role model by gaining the trust and confidence of followers” (Eagly et al. 2003, p. 570).

• The sample data is a subset of the studies in the full meta-analysis, a set of 24 studies that compare men and women in their use of transformational leadership

• Positive effect sizes indicate males score higher than females

Page 11: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

To follow along:

• Open RevMan• Open a review from a file• Open the file named:

Gender_differences_for_transformational_leadership.rm5• Go to Data and analyses on the left-hand menu• Double-click on 1.1 Transformational leadership• NOTE: RevMan uses the assumption that each group has a

different variance component

Page 12: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Page 13: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Page 14: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Page 15: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Summary of results – separate variance estimates for each group

Group k Mean 95% CI τ2 p

Journals 13 -0.05 [-0.24, 0.12] 0.09 <0.001

Dissertations 7 -0.47 [-0.69,-0.26] 0.02 0.22

Unpublished 4 -0.16 [-0.30,-0.03] 0.00 0.87

TOTAL 24 -0.16 [-0.29, -0.03] 0.08 <0.001

•Journals have a significant variance component, and the mean is not different from zero•Dissertations and unpublished studies both have a non-significant variance component, but both find that women score higher on transformational leadership

Page 16: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Summary of results – separate variance estimates for each group (continued)

Group k Mean 95% CI τ2 p

Journals 13 -0.05 [-0.24, 0.12] 0.09 <0.001

Dissertations 7 -0.47 [-0.69,-0.26] 0.02 0.22

Unpublished 4 -0.16 [-0.30,-0.03] 0.00 0.87

TOTAL 24 -0.16 [-0.29, -0.03] 0.08 <0.001

•The test of the variance component as different from zero is exactly the fixed effects test of homogeneity. •To get this test, we compute the test of homogeneity within each group of studies.

Page 17: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Test of between group differences

• To test between group differences in a random effects model, we test whether the variance component for the variation among the random effects means is equal to zero

• There are several ways to obtain this value• We will use a test of homogeneity of the three means – we

will treat the three group means as a meta-analysis

Page 18: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Test of between-group differences

• We will compute a test of homogeneity using our three means as if this is a meta-analysis

• We will use the means and their estimated variances to compute the sums we need to compute the homogeneity test

• These computations are all done “behind the scenes” by RevMan

Page 19: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Computation of Q between groups

Source Mean Var Wt Wt*Mean Wt*Mean2

Journals -0.05 0.008 122.53 -6.13 0.031

Dissertations -0.47 0.012 86.46 -40.64 19.10

Unpublished -0.16 0.005 211.32 -33.82 5.41

SUM 420.31 -80.59 24.54

( 80.59* 80.59)24.54

420.319.09

Q

Compare 9.09 to a chi-square with df=3-1=2. p-value is 0.011

Page 20: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

What happens if we use the same variance component for all groups?

• We will need to try this in Comprehensive Meta-analysis• Open your trial version of Comprehensive Meta-analysis• Check that you will run the trial• Open the file called: leaderage.cma• Data is here:

https://my.vanderbilt.edu/emilytannersmith/training-materials/

Page 21: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Run analyses

Page 22: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Page 23: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Page 24: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Group bypub source

Study name Statistics for each study Hedges's g and 95% CI

Hedges's Standard Lower Upper g error Variance limit limit Z-Value p-Value

1.00 B23 -0.090 0.066 0.004 -0.220 0.040 -1.355 0.1761.00 CA -0.170 0.083 0.007 -0.333 -0.007 -2.045 0.0411.00 CH -0.220 0.118 0.014 -0.451 0.011 -1.868 0.0621.00 CW1 0.610 0.092 0.008 0.430 0.790 6.656 0.0001.00 CW2 0.200 0.150 0.023 -0.095 0.495 1.330 0.1831.00 DF -0.250 0.147 0.022 -0.539 0.039 -1.696 0.0901.00 JB -0.130 0.117 0.014 -0.360 0.100 -1.109 0.2671.00 JL -0.290 0.105 0.011 -0.495 -0.085 -2.768 0.0061.00 KO 0.310 0.078 0.006 0.157 0.463 3.982 0.0001.00 KUU 0.090 0.214 0.046 -0.330 0.510 0.420 0.6751.00 LJ -0.350 0.068 0.005 -0.482 -0.218 -5.185 0.0001.00 RH -0.360 0.087 0.008 -0.531 -0.189 -4.116 0.0001.00 SM 0.000 0.283 0.080 -0.556 0.556 0.000 1.0001.00 -0.055 0.084 0.007 -0.219 0.108 -0.662 0.5083.00 BO -0.620 0.262 0.069 -1.134 -0.106 -2.365 0.0183.00 CU -0.170 0.185 0.034 -0.533 0.193 -0.917 0.3593.00 DA -0.150 0.281 0.079 -0.701 0.401 -0.534 0.5933.00 HI -0.360 0.356 0.127 -1.059 0.339 -1.010 0.3123.00 MCG -0.720 0.242 0.059 -1.194 -0.246 -2.975 0.0033.00 RO -0.440 0.225 0.050 -0.880 0.000 -1.960 0.0503.00 WI -0.870 0.239 0.057 -1.339 -0.401 -3.639 0.0003.00 -0.477 0.141 0.020 -0.752 -0.201 -3.389 0.0014.00 BJ -0.100 0.148 0.022 -0.390 0.190 -0.675 0.5004.00 GM -0.100 0.252 0.064 -0.594 0.394 -0.397 0.6924.00 MA -0.080 0.199 0.040 -0.471 0.311 -0.401 0.6884.00 SP -0.210 0.090 0.008 -0.385 -0.035 -2.346 0.0194.00 -0.130 0.162 0.026 -0.447 0.187 -0.805 0.421Overall -0.159 0.066 0.004 -0.288 -0.031 -2.429 0.015

-1.00 -0.50 0.00 0.50 1.00

Favours A Favours B

Meta Analysis

Meta Analysis

Page 25: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Notes about the CMA forest plot

• Like RevMan, the confidence intervals around each study are the fixed effects confidence intervals (they use the within-study fixed effects variance)

• The group means are the random effects means computed using random effects weights. Their confidence intervals are also use random effects.

• In this example, we are using the same variance component for all groups

Page 26: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Summary from CMA

Page 27: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Notes about CMA results

• We assumed that the variance component was 0.08 for all studies

• Compared to our separate variance estimates, this value is smaller than the separate variance estimate for journals, but larger than the separate estimate for dissertations and unpublished articles

Page 28: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Reporting results from a random effects categorical analysis

Group RE mean RE CI τ3• The assumption made about the random effects variance: separate estimate for each group, or the same estimate for all groups.

• Rationale for the choice of variance component

• The random effects mean and CI• The value of the variance

components (or variance component)

• The test of the between-group differences, and its significance

for between-group means

df and p-value

Q

Page 29: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

What is meta-regression?

• Meta-regression is a statistical technique used in a meta –analysis to examine how characteristics of studies are related to variation in effect sizes across studies

• Meta-regression is analogous to regression analysis but using effect sizes as our outcomes, and information extracted from studies as moderators/predictors

• NOTE: We can conduct a meta-regression in any statistical program. Here we will use CMA. BUT, note that using other standard programs may necessitate some adjustments to the results since they don’t produce exactly what we want.

Page 30: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Meta-regression used to examine heterogeneity

• When we have a heterogeneous set of effect sizes, we can use statistical techniques to examine the association among characteristics of the study and variation among effect sizes

• We have a plan for these analyses a priori – based on our understanding of the literature, and a logic model or framework

• Meta-regression used when we have more than one predictor or moderator (either continuous or categorical)

Page 31: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Form of the meta-regression model

0 1 1 ...i i p ipES B B x B x

1 2

0 1

is our generic effect size for study i

, ,... are the values for the predictor variables for study i

, ,..., are the unknown regression coefficients

i

i i ip

p

ES

x x x

B B B

Page 32: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Recall that the variance of the effect size

• Depends on the sample size for all types of effects we have talked about

• Thus, the precision of each study’s effect size depends on sample size

• This is different from our typical application of regression where we assume every person has the same “weight”

• Thus, we need to use weighted least squares regression to account for the fact that the precision of each effect size depends on sample size

Page 33: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Random effects meta-regression

• As in the categorical analysis discussion, we will need an estimate of the random effects variance for our studies that will be used as our weights in the regression

• There are many ways to compute the variance component in a random effects meta-regression

• For now, let’s assume a single variance component for all studies.

Page 34: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Test for the fit of the meta-regression model• As in a standard regression model, we can use the regression

ANOVA table for diagnostics about the fit of a meta-regression• Recall that in a standard regression analysis, we would get the

following regression ANOVA table:

ANOVAb,c

556.483 2 278.241 6.927 .004a

923.856 23 40.168

1480.338 25

Regression

Residual

Total

Model1

Sum ofSquares df Mean Square F Sig.

Predictors: (Constant), grade, percmina.

Dependent Variable: ztransb.

Weighted Least Squares Regression - Weighted by wtc.

Page 35: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Test of Model Fit in Meta-regression

• In meta-regression, we use the ANOVA table to get two different Q statistics:

• QM – model sum of squares, compare to chi-square distribution with p – 1 df (p is number of predictors in the model)

• QR – residual sum of squares, compare to chi-square distribution with k - p – 1 df (k is the number of studies)

• See Lipsey & Wilson. 2001. Practical Meta-analysis. Thousand Oaks, CA: Sage. pp. 122-124

Page 36: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

QM , the model sum of squares

• Qmodel is the test of whether at least one of the regression coefficients (not including the intercept) is different from zero

• We compare QM to a chi-square distribution with p – 1 degrees of freedom with p = # of predictors in model

• If QM is significant, then at least one of the regression coefficients is different from zero

Page 37: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

QR , the error or residual sum of squares

• QR is the test of whether there is more residual variation than we would expect IF the model “fits” the data

• We compare QR to a chi-square distribution with k - p – 1 degrees of freedom with k = # of studies/effect sizes, and p = # of predictors in model

• If QR is significant, then we have more error or residual variation to explain, or that is not accounted for by the variables we have in the model

Page 38: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Testing significance of individual regression coefficients in meta-regression• In a standard regression analysis, we find the t-tests on the printout to

see which regression coefficients are significantly different from zero• Those significant regression coefficients indicate that these predictors

are associated with the outcome• We will use CMA which gives us the z-tests for the regression

coefficients• NOTE: When doing meta-regression in a standard program like

SPSS, we have to make some adjustments since these programs do not compute the weighted regression in the way we need for meta-analysis

Page 39: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

To conduct a meta-regression in CMA: run an analysis to get to the table below

Page 40: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Under Analyses, choose meta-regression

Page 41: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

On the next page, choose the continuous outcome, averageage

Page 42: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

By default, the analysis will be fixed effects. Choose method of moments under Computational options

Page 43: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Regression of averageage on Hedges's g

averageage

Hed

ges's

g

24.90 28.62 32.34 36.06 39.78 43.50 47.22 50.94 54.66 58.38 62.10

0.80

0.62

0.44

0.26

0.08

-0.10

-0.28

-0.46

-0.64

-0.82

-1.00

Plot of points and regression line

Page 44: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Results

Page 45: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Example for meta-regression

Page 46: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Objective of the review

Page 47: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Interventions

Page 48: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Example from Wilson & Lipsey

Page 49: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

What to report in a random effects meta-regression?• The software and/or method used to compute the results• The method used to compute the random effects variance

component• The goodness of fit tests: Qmodel , and QResidual

• The regression coefficients and their test of significance

Page 50: Moderator analyses:  Categorical models and Meta-regression

Campbell Collaboration Colloquium – May 2012 www.campbellcollaboration.org

Final notes

• Software may be a problem in meta-regression as only CMA computes meta-regression. RevMan does not have the capacity for meta-regression

• CMA only allows one predictor in the meta-regression• To conduct the analyses as seen in the Wilson & Lipsey

example, you need to use other general statistical programs like SPSS, or STATA

• There are R programs available to conduct meta-analyses as well

Page 51: Moderator analyses:  Categorical models and Meta-regression

The Campbell Collaboration www.campbellcollaboration.org

P.O. Box 7004 St. Olavs plass

0130 Oslo, Norway

E-mail: [email protected]

http://www.campbellcollaboration.org