AAAI Publications, Thirty-First AAAI Conference on Artificial Intelligence

Font Size: 
Causal Effect Identification by Adjustment under Confounding and Selection Biases
Juan D. Correa, Elias Bareinboim

Last modified: 2017-02-12

Abstract


Controlling for selection and confounding biases are two of the most challenging problems in the empirical sciences as well as in artificial intelligence tasks. Covariate adjustment (or, Backdoor Adjustment) is the most pervasive technique used for controlling confounding bias, but the same is oblivious to issues of sampling selection. In this paper, we introduce a generalized version of covariate adjustment that simultaneously controls for both confounding and selection biases. We first derive a sufficient and necessary condition for recovering causal effects using covariate adjustment from an observational distribution collected under preferential selection. We then relax this setting to consider cases when additional, unbiased measurements over a set of covariates are available for use (e.g., the age and gender distribution obtained from census data). Finally, we present a complete algorithm with polynomial delay to find all sets of admissible covariates for adjustment when confounding and selection biases are simultaneously present and unbiased data is available.

Keywords


effects of interventions; identifiability; control of confounding; sampling selection bias; back-door criterion

Full Text: PDF