Minimax Optimal Nonparametric Estimation of Heterogeneous Treatment Effects

TL;DR

This paper establishes the optimal statistical limits for nonparametric estimation of heterogeneous treatment effects, proposing a near minimax optimal estimator that adapts to covariate geometry and density ratios.

Contribution

It models HTE as a smooth difference of baseline functions and derives tight bounds, introducing a novel estimator and a new maximal inequality for covariate density analysis.

Findings

The proposed estimator is near minimax optimal.

The analysis accounts for covariate geometry and density ratios.

A new maximal inequality is introduced for covariate density analysis.

Abstract

A central goal of causal inference is to detect and estimate the treatment effects of a given treatment or intervention on an outcome variable of interest, where a member known as the heterogeneous treatment effect (HTE) is of growing popularity in recent practical applications such as the personalized medicine. In this paper, we model the HTE as a smooth nonparametric difference between two less smooth baseline functions, and determine the tight statistical limits of the nonparametric HTE estimation as a function of the covariate geometry. In particular, a two-stage nearest-neighbor-based estimator throwing away observations with poor matching quality is near minimax optimal. We also establish the tight dependence on the density ratio without the usual assumption that the covariate densities are bounded away from zero, where a key step is to employ a novel maximal inequality which could be of independent interest.