Estimation and Inference for Causal Explainability
By: Weihan Zhang, Zijun Gao
Understanding how much each variable contributes to an outcome is a central question across disciplines. A causal view of explainability is favorable for its ability in uncovering underlying mechanisms and generalizing to new contexts. Based on a family of causal explainability quantities, we develop methods for their estimation and inference. In particular, we construct a one-step correction estimator using semi-parametric efficiency theory, which explicitly leverages the independence structure of variables to reduce the asymptotic variance. For a null hypothesis on the boundary, i.e., zero explainability, we show its equivalence to Fisher's sharp null, which motivates a randomization-based inference procedure. Finally, we illustrate the empirical efficacy of our approach through simulations as well as an immigration experiment dataset, where we investigate how features and their interactions shape public opinion toward admitting immigrants.
Similar Papers
On robust Bayesian causal inference
Methodology
Finds true causes even with missing information.
On robust Bayesian causal inference
Methodology
Finds true causes even with missing information.
Bayesian Inference for Confounding Variables and Limited Information
Methodology
Finds hidden problems in data.