Kernel Optimal Orthogonality Weighting: A Balancing Approach to Estimating Effects of Continuous Treatments

Many scientific questions require estimating the effects of continuous treatments. Outcome modeling and weighted regression based on the generalized propensity score are the most commonly used methods to evaluate continuous effects. However, these techniques may be sensitive to model misspecification, extreme weights or both. In this paper, we propose Kernel Optimal Orthogonality Weighting (KOOW), a convex optimization-based method, for estimating the effects of continuous treatments. KOOW finds weights that minimize the worst-case penalized functional covariance between the continuous treatment and the confounders. This material is based upon work supported by the National Science Foundation under Grants Nos. Using data from the Women's Health Initiative observational study, we apply KOOW to evaluate the effect of red meat consumption on blood pressure. Keywords: Independence, continuous actions, policy evaluation, causal inference, optimization, covariate balance 2 1 Introduction The questions that motivate many scientific studies require estimating the effects of continuous treatments. Continuous treatments are usually indexed by doses and their relationships with the outcome are described by dose-response curves.