A0194
Title: HNCI: High-dimensional network causal inference
Authors: Wenqin Du - University of Southern California (United States) [presenting]
Rundong Ding - University of Southern California (United States)
Yingying Fan - University of Southern California (United States)
Jinchi Lv - University of Southern California (United States)
Abstract: The problem of evaluating the effectiveness of a treatment or policy commonly appears in causal inference applications under network interference. The new method of high-dimensional network causal inference (HNCI) is suggested, which provides both a valid confidence interval on the average direct treatment effect on the treated (ADET) and a valid confidence set for the neighborhood size for the interference effect. The method accommodates certain types of heterogeneity in node interference neighborhood sizes. A linear regression formulation of potential outcomes is proposed, where the regression coefficients correspond to the underlying true interference function values of nodes and exhibit a latent homogeneous structure. Such a formulation allows leveraging existing literature from linear regression and homogeneity pursuit to conduct valid statistical inferences with theoretical guarantees. The resulting confidence intervals for the ADET are formally justified through asymptotic normality with estimable variances. The confidence set for the neighborhood size is further provided with theoretical guarantees exploiting the repro samples approach. The practical utilities of the newly suggested methods are demonstrated through simulation and real data examples.
