Causal inference and the data-fusion problem

TLDR

The growing availability of heterogeneous datasets offers unprecedented opportunities for insights that cannot be derived from single sources, but also introduces biases such as confounding, sampling selection, and cross‑population effects that existing parametric methods have only partially addressed. The authors aim to unify causal analysis methods and provide a general nonparametric framework that solves the data‑fusion problem in causal inference. They develop a nonparametric framework that integrates multiple heterogeneous datasets, correcting for confounding, sampling selection, and cross‑population biases to enable valid causal queries.

Abstract

We review concepts, principles, and tools that unify current approaches to causal analysis and attend to new challenges presented by big data. In particular, we address the problem of data fusion-piecing together multiple datasets collected under heterogeneous conditions (i.e., different populations, regimes, and sampling methods) to obtain valid answers to queries of interest. The availability of multiple heterogeneous datasets presents new opportunities to big data analysts, because the knowledge that can be acquired from combined data would not be possible from any individual source alone. However, the biases that emerge in heterogeneous environments require new analytical tools. Some of these biases, including confounding, sampling selection, and cross-population biases, have been addressed in isolation, largely in restricted parametric models. We here present a general, nonparametric framework for handling these biases and, ultimately, a theoretical solution to the problem of data fusion in causal inference tasks.