Selected Statistical Issues in Group Randomized Trials

Abstract

Key Words correlated data, generalized estimating equations (GEE), generalized linear mixed models (GLMM), permutation tests, matched design s Abstract Group randomized trials (GRTs) in public health research typically use a small number of randomized groups with a relatively large number of participants per group. Two fundamental features characterize GRTs: a positive correlation of outcomes within a group, and the small number of groups. Appropriate consideration of these fundamental features is essential for design and analysis. This paper presents the fundamental features of GRTs and the importance of considering these features in design and analysis. It also reviews and contrasts the main analytic methods proposed for GRTs, emphasizing the assumptions required to make these methods valid and efficient. Also discussed are various design issues, along with guidelines for choosing among them. A real data example illustrates these issues and methods.

Covariance estimators for Generalized Estimating Equations (GEE) in longitudinal analysis with small samples

“…There exists within-subject correlation, but the observations across subjects are assumed to be independent. In addition, the marginal model specifying an association between μ ij and the covariates of interest X ij is given by (1) with g as a known link function, β an unknown p × 1 vector of regression coefficients. The conditional variance of Y ij given X ij is Var(Y ij |X ij ) = ν(μ ij )ϕ with ν as a known variance function of μ ij and ϕ a scale parameter which may need to be estimated.…”

“…Longitudinal data is commonly encountered in biomedical studies [1,2,3,4]. For example, in a diabetes study, repeated primary efficacy measures on HbA1c were taken over time (baseline and follow-up visits after treatment) for each patient, and the question of interest was to investigate the trend of HbA1c changing over time or the insulin treatment effect on HbA1c [5].…”

Does School Integration Generate Peer Effects? Evidence from Boston's Metco Program

“…In practice, the standard errors from this procedure may be misleading, especially when there are few clusters, and inference using grouped data has been shown to be more reliable (see, e.g., Feng, et al, 2001;or Donald and Lang, 2001). This leads us to report results using both cell means and individuals.…”

A Comparison of the Statistical Power of Different Methods for the Analysis of Repeated Cross-Sectional Cluster Randomization Trials with Binary Outcomes

“…Using this design, the response is measured on a sample of subjects from each cluster following the treatment intervention. Several authors have described statistical methods for the analysis of these trials (Donner and Klar, 2000;Donner and Klar, 1994;Donner and Donald, 1988;Klar et al, 1995;Bellamy et al, 2000;Klar and Donner, 2001;Donner, 1999;Feng et al, 2001;Omar and Thompson, 2000). A recent study compared the relative statistical power of different methods for the analysis of completely randomized cross-sectional cluster randomization trials with binary outcomes (Austin, 2007).…”