It is well known that incorporating auxiliary covariates in the analysis of randomized clinical trials (RCTs) can increase efficiency. Questions still remain regarding how to flexibly incorporate baseline covariates while maintaining valid inference. Recent methodological advances that use semiparametric theory to develop covariate-adjusted inference for RCTs have focused on independent outcomes. In biomedical research, however, cluster randomized trials and longitudinal studies, characterized by correlated responses, are commonly used. We develop methods that flexibly incorporate baseline covariates for efficiency improvement in randomized studies with correlated outcomes. In Chapter 1, we show how augmented estimators may be used for cluster randomized trials, in which treatments are assigned to groups of individuals. We demonstrate the potential for imbalance correction and efficiency improvement through consideration of both cluster- and individual-level covariates. To improve small-sample estimation, we consider several variance adjustments. We evaluate this approach for continuous and binary outcomes through simulation and apply it to the Young Citizens study, a cluster randomized trial of a community behavioral intervention for HIV prevention in Tanzania. Chapter 2 builds upon the previous chapter by deriving semiparametric locally efficient estimators of marginal mean treatment effects when outcomes are correlated. Estimating equations are determined by the efficient score under a mean model for marginal effects when data contain baseline covariates and exhibit correlation. Locally efficient estimators are implemented for longitudinal data with continuous outcomes and clustered data with binary outcomes. Methods are illustrated through application to AIDS Clinical Trial Group Study 398, a longitudinal randomized study that compared various protease inhibitors in HIV-positive subjects. In Chapter 3, we empirically evaluate several covariate-adjusted tests of intervention effects when baseline covariates are selected adaptively and the number of randomized units is small. We demonstrate that randomization inference preserves type I error under model selection while tests based on asymptotic theory break down. Additionally, we show that covariate adjustment typically increases power, except at extremely small sample sizes using liberal selection procedures. Properties of covariate-adjusted tests are explored for independent and multivariate outcomes. We revisit Young Citizens to provide further insight into the performance of various methods in small-sample settings.
Identifer | oai:union.ndltd.org:harvard.edu/oai:dash.harvard.edu:1/9453701 |
Date | 21 June 2014 |
Creators | Stephens, Alisa Jane |
Contributors | De Gruttola, Victor Gerard, Tchetgen Tchetgen, Eric Joel |
Publisher | Harvard University |
Source Sets | Harvard University |
Language | en_US |
Detected Language | English |
Type | Thesis or Dissertation |
Rights | open |
Page generated in 0.0013 seconds