Beyond Interaction Effects: Two Logics for Studying Population Inequalities

TL;DR

This paper compares traditional deductive interaction models with inductive machine learning approaches for studying population inequalities, highlighting their tradeoffs and providing a framework for choosing between them.

Contribution

It develops a framework to navigate between deductive and inductive methods in inequality research, emphasizing their respective strengths and appropriate contexts.

Findings

Simulation shows when each approach performs best

Tradeoff identified between interpretability and flexibility

Framework aids researchers in method selection for inequality analysis

Abstract

When sociologists and other social scientist ask whether the return to college differs by race and gender, they face a choice between two fundamentally different modes of inquiry. Traditional interaction models follow deductive logic: the researcher specifies which variables moderate effects and tests these hypotheses. Machine learning methods follow inductive logic: algorithms search across vast combinatorial spaces to discover patterns of heterogeneity. This article develops a framework for navigating between these approaches. We show that the choice between deduction and induction reflects a tradeoff between interpretability and flexibility, and we demonstrate through simulation when each approach excels. Our framework is particularly relevant for inequality research, where understanding how treatment effects vary across intersecting social subpopulation is substantively central.