Confounder Selection via Support Intersection
This addresses confounder selection for causal inference in observational studies, representing an incremental improvement over existing methods.
The paper tackles the problem of confounder selection in high-dimensional observational studies where traditional variable selection methods fail, proposing several methods based on support intersection under a sparsity assumption. It provides numerical simulations and real dataset applications to support the claims, though no specific performance numbers are mentioned.
Confounding matters in almost all observational studies that focus on causality. In order to eliminate bias caused by connfounders, oftentimes a substantial number of features need to be collected in the analysis. In this case, large p small n problem can arise and dimensional reduction technique is required. However, the traditional variable selection methods which focus on prediction are problematic in this setting. Throughout this paper, we analyze this issue in detail and assume the sparsity of confounders which is different from the previous works. Under this assumption we propose several variable selection methods based on support intersection to pick out the confounders. Also we discussed the different approaches for estimation of causal effect and unconfoundedness test. To aid in our description, finally we provide numerical simulations to support our claims and compare to common heuristic methods, as well as applications on real dataset.