Modeling Covariate Transition for Efficient Estimation of Longitudinal Treatment Effects in Randomized Experiments

We present a regression-adjustment framework designed to estimate longitudinal treatment effects in randomized experiments under static regimes. Although regression-adjustment methods are useful for variance reduction in randomized experiments through the use of pre-treatment covariates, they usually focus only on average effects, which cannot capture valuable knowledge about when effects appear and how long they continue. To address this limitation, we need to consider intermediate outcomes and evolving post-treatment covariates over time, and we represent these transitions using transition kernels. Furthermore, we establish the asymptotic normality and the semiparametric efficiency bound for our estimator, enabling more powerful statistical inference. Simulation studies and empirical analysis using A/B test data from a streaming platform in Japan demonstrate the practical advantages of our method.