What can the millions of random treatments in nonexperimental data reveal about causes?

TL;DR

This paper introduces a Bayesian method leveraging pairwise differences in nonexperimental data to estimate causal effects more accurately, expanding observational data into a quasi-experimental framework and recovering individual effects.

Contribution

It proposes a novel Bayesian approach that combines pairwise treatment differences to improve causal inference from large nonexperimental datasets.

Findings

Outperforms traditional estimators in simulations and real data.

Recovers individual causal effects in heterogeneous populations.

Effectively scales to large observational datasets.

Abstract

We propose a new method to estimate causal effects from nonexperimental data. Each pair of sample units is first associated with a stochastic 'treatment' - differences in factors between units - and an effect - a resultant outcome difference. It is then proposed that all such pairs can be combined to provide more accurate estimates of causal effects in observational data, provided a statistical model connecting combinatorial properties of treatments to the accuracy and unbiasedness of their effects. The article introduces one such model and a Bayesian approach to combine the $O(n^2)$ pairwise observations typically available in nonexperimnetal data. This also leads to an interpretation of nonexperimental datasets as incomplete, or noisy, versions of ideal factorial experimental designs. This approach to causal effect estimation has several advantages: (1) it expands the number of observations, converting thousands of individuals into millions of observational treatments; (2) starting with treatments closest to the experimental ideal, it identifies noncausal variables that can be ignored in the future, making estimation easier in each subsequent iteration while departing minimally from experiment-like conditions; (3) it recovers individual causal effects in heterogeneous populations. We evaluate the method in simulations and the National Supported Work (NSW) program, an intensively studied program whose effects are known from randomized field experiments. We demonstrate that the proposed approach recovers causal effects in common NSW samples, as well as in arbitrary subpopulations and an order-of-magnitude larger supersample with the entire national program data, outperforming Statistical, Econometrics and Machine Learning estimators in all cases...