Open Access
2011 Comparison of methods for fixed effect meta-regression of standardized differences of means
Michael J. Malloy, Luke A. Prendergast, Robert G. Staudte
Electron. J. Statist. 5: 83-101 (2011). DOI: 10.1214/11-EJS598


Given a number of different studies estimating the same effect size, it is often desired to explain heterogeneity of outcomes using concomitant covariates. For very large sample sizes, effect size estimates are approximately normally distributed and a straightforward application of weighted least squares is appropriate. However in practice within study sample variances are often small to moderate, casting doubt on the normality assumption for effect sizes and results based on weighted least squares. One can alternatively variance stabilize the effect size estimates and adopt a generalized linear model. Both methods are compared on two examples when effect sizes are the standardized difference of means. Then simulation studies are conducted to compare the coverage and width of confidence intervals for the meta-regression coefficients. These simulations show that the coverage probability associated with weighted least squares can be well below the nominated level for small to moderate sample sizes. Further empirical investigations reveal a bias in estimation due to using estimated weights which were assumed to be known. For these models, the generalized linear model approach resulted in much improved coverage probabilities.


Download Citation

Michael J. Malloy. Luke A. Prendergast. Robert G. Staudte. "Comparison of methods for fixed effect meta-regression of standardized differences of means." Electron. J. Statist. 5 83 - 101, 2011.


Published: 2011
First available in Project Euclid: 25 February 2011

zbMATH: 1274.62452
MathSciNet: MR2773609
Digital Object Identifier: 10.1214/11-EJS598

Primary: 62J05
Secondary: 62J12

Keywords: generalized linear model , weighted least squares

Rights: Copyright © 2011 The Institute of Mathematical Statistics and the Bernoulli Society

Back to Top