A Stable and Efficient Covariate-Balancing Estimator for Causal Survival Effects

arXiv:2310.02278v2 Announce Type: replace-cross
Abstract: We propose an empirically stable and asymptotically efficient covariate-balancing approach to the problem of estimating survival causal effects in data with conditionally-independent censoring. This addresses a challenge often encountered in state-of-the-art nonparametric methods: the use of inverses of small estimated probabilities and the resulting amplification of estimation error. We validate our theoretical results in experiments on synthetic and semi-synthetic data.

abstract art arxiv causal challenge data effects estimator independent replace small state stat.me stat.ml survival type