Automated versus do-it-yourself methods for causal inference: Lessons learned from a data analysis competition

TL;DR

This paper analyzes a 2016 causal inference data analysis competition, comparing automated and do-it-yourself methods, revealing that flexible response surface modeling improves performance, and proposing new combined methods.

Contribution

It provides a comparative evaluation of various causal inference strategies from a major competition and introduces new hybrid methods based on top performers.

Findings

Flexible response surface modeling outperforms other methods.

Automated methods perform comparably to do-it-yourself approaches.

Characteristics of data influence method performance.

Abstract

Statisticians have made great progress in creating methods that reduce our reliance on parametric assumptions. However this explosion in research has resulted in a breadth of inferential strategies that both create opportunities for more reliable inference as well as complicate the choices that an applied researcher has to make and defend. Relatedly, researchers advocating for new methods typically compare their method to at best 2 or 3 other causal inference strategies and test using simulations that may or may not be designed to equally tease out flaws in all the competing methods. The causal inference data analysis challenge, "Is Your SATT Where It's At?", launched as part of the 2016 Atlantic Causal Inference Conference, sought to make progress with respect to both of these issues. The researchers creating the data testing grounds were distinct from the researchers submitting methods whose efficacy would be evaluated. Results from 30 competitors across the two versions of the competition (black box algorithms and do-it-yourself analyses) are presented along with post-hoc analyses that reveal information about the characteristics of causal inference strategies and settings that affect performance. The most consistent conclusion was that methods that flexibly model the response surface perform better overall than methods that fail to do so. Finally new methods are proposed that combine features of several of the top-performing submitted methods.