|
Activity Number:
|
27
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, July 29, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
IMS
|
| Abstract - #308207 |
|
Title:
|
Hierarchical Dependence in Meta-Analysis
|
|
Author(s):
|
John R. Stevens*+ and Alan M. Taylor
|
|
Companies:
|
Utah State University and Brigham Young University-Idaho
|
|
Address:
|
3900 Old Main Hill, Logan, UT, 84322-3900,
|
|
Keywords:
|
meta-analysis ; dependence structure
|
|
Abstract:
|
A meta-analysis traditionally assumes the independence of study results. In cases where this assumption is violated, the dependence among study results can be estimated and accounted for at the sampling level in the meta-analysis to avoid overlapping information. We present an approach to account for the dependence at the hierarchical level also, effectively down-weighting extreme effect size estimates that are hierarchically dependent. This hierarchical dependence is estimated using both random effects and Bayesian models. We apply this approach to a meta-analysis of studies examining the effect of native language vocabulary aids on second language reading comprehension. Application to gene expression studies is also discussed.
|
