ST ] 2 8 M ay 2 01 8 1 Model-Robust Counterfactual Prediction Method

Content Provider	Semantic Scholar
Author	Zachariah, Dave Stoica, Petre
Copyright Year	2018
Abstract	We develop a novel method for counterfactual analysis based on observational data using prediction intervals for units under different exposures. Unlike methods that target heterogeneous or conditional average treatment effects of an exposure, the proposed approach aims to take into account the irreducible dispersions of counterfactual outcomes so as to quantify the relative impact of different exposures. The prediction intervals are constructed in a distribution-free and modelrobust manner based on the conformal prediction approach. The computational obstacles to this approach are circumvented by leveraging properties of a tuning-free method that learns sparse additive predictor models for counterfactual outcomes. The method is illustrated using both real and synthetic data.
File Format	PDF HTM / HTML
Alternate Webpage(s)	http://arxiv-export-lb.library.cornell.edu/pdf/1705.07019
Language	English
Access Restriction	Open
Content Type	Text
Resource Type	Article