Document Detail


A mixed model-based variance estimator for marginal model analyses of cluster randomized trials.
MedLine Citation:
PMID:  17623344     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
Generalized estimating equations (GEE) are used in the analysis of cluster randomized trials (CRTs) because: 1) the resulting intervention effect estimate has the desired marginal or population-averaged interpretation, and 2) most statistical packages contain programs for GEE. However, GEE tends to underestimate the standard error of the intervention effect estimate in CRTs. In contrast, penalized quasi-likelihood (PQL) estimates the standard error of the intervention effect in CRTs much better than GEE but is used less frequently because: 1) it generates an intervention effect estimate with a conditional, or cluster-specific, interpretation, and 2) PQL is not a part of most statistical packages. We propose taking the variance estimator from PQL and re-expressing it as a sandwich-type estimator that could be easily incorporated into existing GEE packages, thereby making GEE useful for the analysis of CRTs. Using numerical examples and data from an actual CRT, we compare the performance of this variance estimator to others proposed in the literature, and we find that our variance estimator performs as well as or better than its competitors.
Authors:
Thomas M Braun
Related Documents :
22028944 - Is the even distribution of insecticide-treated cattle essential for tsetse control? mo...
21978424 - Modelling of organic matter dynamics during the composting process.
22254674 - Ambient assisted living spaces validation by services and devices simulation.
21911214 - Description and computational modeling of the whole course of status epilepticus induce...
15891824 - Does the commonly used estimator of nutrient resorption in tree foliage actually measur...
12116654 - Assessment of the accuracy of matrix representation with parsimony analysis supertree c...
Publication Detail:
Type:  Journal Article; Research Support, N.I.H., Extramural    
Journal Detail:
Title:  Biometrical journal. Biometrische Zeitschrift     Volume:  49     ISSN:  0323-3847     ISO Abbreviation:  Biom J     Publication Date:  2007 Jun 
Date Detail:
Created Date:  2007-07-17     Completed Date:  2007-08-17     Revised Date:  2007-11-15    
Medline Journal Info:
Nlm Unique ID:  7708048     Medline TA:  Biom J     Country:  Germany    
Other Details:
Languages:  eng     Pagination:  394-405     Citation Subset:  IM    
Affiliation:
Department of Biostatistics, University of Michigan, 1420 Washington Heights, M4063 SPH II, Ann Arbor, MI 48109, USA. tombraun@umich.edu
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Cluster Analysis
Data Interpretation, Statistical
Models, Statistical*
Randomized Controlled Trials as Topic*
Grant Support
ID/Acronym/Agency:
5 P30 CA46592/CA/NCI NIH HHS

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Estimating treatment effect heterogeneity for binary outcomes via Dirichlet multinomial constraints.
Next Document:  Analysis of relation between virologic responses and immunologic responses, patient's factors in AID...