Are you Phillip J. Schulte?

Claim your profile

Publications (1)2.74 Total impact

  • Source
    Phillip J. Schulte · Anastasios A. Tsiatis · Eric B. Laber · Marie Davidian ·
    [Show abstract] [Hide abstract]
    ABSTRACT: In clinical practice, physicians make a series of treatment decisions over the course of a patient's disease based on his/her baseline and evolving characteristics. A dynamic treatment regime is a set of sequential decision rules that operationalizes this process. Each rule corresponds to a key decision point and dictates the next treatment action among the options available as a function of accrued information on the patient. Using data from a clinical trial or observational study, a key goal is estimating the optimal regime, that, if followed by the patient population, would yield the most favorable outcome on average. Q-learning and advantage (A-)learning are two main approaches for this purpose. We provide a detailed account of Q- and A-learning and study systematically the performance of these methods. The methods are illustrated using data from a study of depression.
    Statistical Science 02/2012; 29(4). DOI:10.1214/13-STS450 · 2.74 Impact Factor