"Everything should be made as simple as possible, but not simpler." - Albert Einstein

Seminar Announcement

Inference for Optimal Dynamic Treatment Regimes Using an Adaptive m-out-of-n Bootstrap Scheme

Bibhas Chakraborty, Department of Biostatistics, Columbia University

Monday, April 16, 2012

4:00 p.m., room 223, Weber Bldg

ABSTRACT

A dynamic treatment regime (DTR) consists of a set of decision rules that dictate how to personalize treatment to patients based on available treatment and covariate history. A common method for estimating an optimal DTR from patient data is Q-learning which involves nonsmooth operations of the data. This nonsmoothness causes standard asymptotic approaches for inference like the bootstrap or Taylor series arguments to break down if applied without correction. Here we present an adaptive m-out-of-n bootstrap procedure for constructing confidence intervals for the parameters indexing the optimal dynamic regime. The proposed method produce asymptotically correct confidence sets, and has the advantage of being conceptually simple. We provide an extensive simulation study to compare our proposed method with currently available inference procedures. Analysis of the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) study is used as an illustrative example of our methodology.

*This is joint work with Eric B. Laber of the North Carolina State University.