Quantifying the impact of fixed effects modeling of clusters in multiple imputation for cluster randomized trials

被引:59
作者
Andridge, Rebecca R. [1 ]
机构
[1] Ohio State Univ, Coll Publ Hlth, Div Biostat, Columbus, OH 43220 USA
关键词
Cluster randomized; Missing data; Multiple imputation; COMMUNITIES; CARE;
D O I
10.1002/bimj.201000140
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
In cluster randomized trials (CRTs), identifiable clusters rather than individuals are randomized to study groups. Resulting data often consist of a small number of clusters with correlated observations within a treatment group. Missing data often present a problem in the analysis of such trials, and multiple imputation (MI) has been used to create complete data sets, enabling subsequent analysis with well-established analysis methods for CRTs. We discuss strategies for accounting for clustering when multiply imputing a missing continuous outcome, focusing on estimation of the variance of group means as used in an adjusted t-test or ANOVA. These analysis procedures are congenial to (can be derived from) a mixed effects imputation model; however, this imputation procedure is not yet available in commercial statistical software. An alternative approach that is readily available and has been used in recent studies is to include fixed effects for cluster, but the impact of using this convenient method has not been studied. We show that under this imputation model the MI variance estimator is positively biased and that smaller intraclass correlations (ICCs) lead to larger overestimation of the MI variance. Analytical expressions for the bias of the variance estimator are derived in the case of data missing completely at random, and cases in which data are missing at random are illustrated through simulation. Finally, various imputation methods are applied to data from the Detroit Middle School Asthma Project, a recent school-based CRT, and differences in inference are compared.
引用
收藏
页码:57 / 74
页数:18
相关论文
共 38 条
[1]  
[Anonymous], 1998, Design and Analysis of Group-Randomized Trials
[2]  
[Anonymous], 2000, SURV METHODOL
[3]  
[Anonymous], NORM WINDOWS 95 98 N
[4]  
[Anonymous], J STAT SOFT IN PRESS
[5]   Small-sample degrees of freedom with multiple imputation [J].
Barnard, J ;
Rubin, DB .
BIOMETRIKA, 1999, 86 (04) :948-955
[6]   Design and Analysis of the Community Youth Development Study Longitudinal Cohort Sample [J].
Brown, Eric C. ;
Graham, John W. ;
Hawkins, J. David ;
Arthur, Michael W. ;
Baldwin, Megan M. ;
Oesterle, Sabrina ;
Briney, John S. ;
Catalano, Richard F. ;
Abbott, Robert D. .
EVALUATION REVIEW, 2009, 33 (04) :311-334
[7]   An Evaluation of Asthma Interventions for Preteen Students [J].
Clark, Noreen M. ;
Shah, Smita ;
Dodge, Julia A. ;
Thomas, Lara J. ;
Andridge, Rebecca R. ;
Little, Roderick J. A. .
JOURNAL OF SCHOOL HEALTH, 2010, 80 (02) :80-87
[8]   CLUSTER RANDOMIZATION TRIALS IN EPIDEMIOLOGY - THEORY AND APPLICATION [J].
DONNER, A ;
KLAR, N .
JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 1994, 42 (1-2) :37-56
[9]  
Donner AK., 2000, DESIGN ANAL CLUSTER
[10]   CONTROL VERSUS AUTONOMY DURING EARLY ADOLESCENCE [J].
ECCLES, JS ;
BUCHANAN, CM ;
FLANAGAN, C ;
FULIGNI, A ;
MIDGLEY, C ;
YEE, D .
JOURNAL OF SOCIAL ISSUES, 1991, 47 (04) :53-68