A0762
Title: Nonparametric estimation of general mediation effects by calibration weighting
Authors: Lukang Huang - Nankai University (China) [presenting]
Zheng Zhang - Renmin University of China (China)
Abstract: To investigate causal mechanisms, causal mediation analysis decomposes the total treatment effect into the natural direct and indirect effects. The aim is to examine the estimation of the direct and indirect effects in a general treatment effect model, where the treatment could be binary, multi-valued, continuous, or mixture valued. We propose generalized weighting estimators with weights estimated by solving an expanding set of equations. Under some sufficient conditions, we show that the proposed estimators are consistent and asymptotically normal. Specifically, when the treatment is discrete, the proposed estimators attain the semi-parametric efficiency bounds. Meanwhile, when the treatment is continuous, the convergence rates of the proposed estimators are slower than root N; however, they are still more efficient than that constructed from the true weighting function. Moreover, a simulation study reveals that our estimators exhibit a satisfactory finite-sample performance, while an application shows its practical value.
