In this chapter, we consider semi-parametric approaches to finding the optimal dynamic treatment regime via modeling contrasts of conditional mean outcomes. In particular, we present G-estimation and regret-based methods including an iterative minimization method. We elucidate the connections between the different types of models assumed (e.g. blips, regrets, and Q-functions) as well as the estimation approaches themselves.
CITATION STYLE
Chakraborty, B., & Moodie, E. E. M. (2013). Semi-parametric Estimation of Optimal DTRs by Modeling Contrasts of Conditional Mean Outcomes (pp. 53–78). https://doi.org/10.1007/978-1-4614-7428-9_4
Mendeley helps you to discover research relevant for your work.