Model-Robust Counterfactual Prediction Method

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 model-robust 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.

[1]  Christopher Winship,et al.  Counterfactuals and Causal Inference by Stephen L. Morgan , 2014 .

[2]  J. Angrist,et al.  Does Compulsory School Attendance Affect Schooling and Earnings? , 1990 .

[3]  J. Pearl Causal inference in statistics: An overview , 2009 .

[4]  D. Rubin Estimating causal effects of treatments in randomized and nonrandomized studies. , 1974 .

[5]  Victor Chernozhukov,et al.  Inference on Treatment Effects after Selection Amongst High-Dimensional Controls , 2011 .

[6]  J. Esarey Causal Inference with Observational Data , 2015 .

[7]  A. Sjölander The Language of Potential Outcomes , 2012 .

[8]  Stefan Wager,et al.  Estimation and Inference of Heterogeneous Treatment Effects using Random Forests , 2015, Journal of the American Statistical Association.

[9]  Illtyd Trethowan Causality , 1938 .

[10]  Jennifer L. Hill,et al.  Bayesian Nonparametric Modeling for Causal Inference , 2011 .

[11]  David M Kent,et al.  Limitations of applying summary results of clinical trials to individual patients: the need for risk stratification. , 2007, JAMA.

[12]  James M. Robins,et al.  Single World Intervention Graphs : A Primer , 2013 .

[13]  W. Gasarch,et al.  The Book Review Column 1 Coverage Untyped Systems Simple Types Recursive Types Higher-order Systems General Impression 3 Organization, and Contents of the Book , 2022 .

[14]  Judea Pearl,et al.  Causal Inference , 2010 .

[15]  Kevin Leyton-Brown,et al.  Counterfactual Prediction with Deep Instrumental Variables Networks , 2016, ArXiv.

[16]  S. Greenland Causal Inference as a Prediction Problem: Assumptions, Identification and Evidence Synthesis , 2012 .

[17]  J. Robins,et al.  Toward a curse of dimensionality appropriate (CODA) asymptotic theory for semi-parametric models. , 1997, Statistics in medicine.

[18]  Christian Hansen,et al.  Double/Debiased/Neyman Machine Learning of Treatment Effects , 2017, 1701.08687.

[19]  M. Farrell Robust Inference on Average Treatment Effects with Possibly More Covariates than Observations , 2015 .

[20]  Alessandro Rinaldo,et al.  Distribution-Free Predictive Inference for Regression , 2016, Journal of the American Statistical Association.

[21]  Stuart Barber,et al.  All of Statistics: a Concise Course in Statistical Inference , 2005 .

[22]  Thomas B. Schön,et al.  Online Learning for Distribution-Free Prediction , 2017, ArXiv.