Title: Hierarchical Bayesian bootstrap for heterogeneous treatment effect estimation
Authors: Arman Oganisian - Brown University (United States) [presenting]
Nandita Mitra - University of Pennsylvania (United States)
Jason Roy - Rutgers University (United States)
Abstract: A major focus of causal inference is the estimation of heterogeneous average treatment effects (HTE) - average treatment effects within strata of another variable of interest such as levels of a biomarker, education, or age strata. Inference involves estimating a stratum-specific regression and integrating it over the distribution of confounders in that stratum - which itself must be estimated. Standard practice involves estimating these stratum-specific confounder distributions independently (e.g. via the empirical distribution or Bayesian bootstrap), which becomes problematic for sparsely populated strata with few observed confounder vectors. We develop a hierarchical Bayesian bootstrap (HBB) prior that induces a dependence across the stratum-specific confounder distributions. The HBB partially pools the stratum-specific distributions, allowing principled borrowing of confounder information across strata when sparsity is a concern. We show that posterior inference under the HBB can yield efficiency gains over standard marginalization approaches while avoiding strong parametric assumptions about the confounder distribution.