Journal
SCANDINAVIAN JOURNAL OF STATISTICS
Volume 34, Issue 3, Pages 478-498Publisher
BLACKWELL PUBLISHING
DOI: 10.1111/j.1467-9469.2006.00555.x
Keywords
causal diagrams; causal inference; interference between subjects; inverse weighting; marginal structural models; semi-parametric efficiency; SUTVA
Categories
Ask authors/readers for more resources
In the analysis of clustered and/or longitudinal data, it is usually desirable to ignore covariate information for other cluster members as well as future covariate information when predicting outcome for a given subject at a given time. This can be accomplished through con-ditional mean models which merely condition on the considered subject's covariate history at each time. Pepe & Anderson (Commun. Stat. Simul. Comput. 23, 1994, 939) have shown that ordinary generalized estimating equations may yield biased estimates for the parameters in such models, but that valid inferences can be guaranteed by using a diagonal working covariance matrix in the equations. In this paper, we provide insight into the nature of this problem by uncovering substantive data-generating mechanisms under which such biases will result. We then propose a class of asymptotically unbiased estimators for the parameters indexing the suggested conditional mean models. In addition, we provide a representation for the efficient estimator in our class, which attains the semi-parametric efficiency bound under the model, along with an efficient algorithm for calculating it. This algorithm is easy to apply and may realize major efficiency improvements as demonstrated through simulation studies. The results suggest ways to improve the efficiency of inverse-probability-of-treatment estimators which adjust for time-varying confounding, and are used to estimate the effect of discontinuing highly active anti-retroviral therapy (HAART) on viral load in HIV-infected patients.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available