Causal Inference in Conjoint Analysis: Understanding Multidimensional Choices Via Stated Preference Experiments

TLDR

Survey experiments are a core tool for causal inference, but their design prevents identification of which components of a multidimensional treatment are influential. The study shows how conjoint analysis can estimate causal effects of multiple treatment components and assess several causal hypotheses simultaneously, and undertakes a formal identification analysis to integrate it with the potential outcomes framework. Conjoint analysis involves respondents scoring alternatives with randomly varied attributes, and the authors propose a new causal estimand that can be nonparametrically identified and easily estimated from conjoint data using a fully randomized design. The new causal estimand is nonparametrically identified and easily estimated from conjoint data, and the authors demonstrate its value through empirical applications to voter decision‑making and attitudes toward immigrants.

Abstract

Survey experiments are a core tool for causal inference. Yet, the design of classical survey experiments prevents them from identifying which components of a multidimensional treatment are influential. Here, we show how conjoint analysis, an experimental design yet to be widely applied in political science, enables researchers to estimate the causal effects of multiple treatment components and assess several causal hypotheses simultaneously. In conjoint analysis, respondents score a set of alternatives, where each has randomly varied attributes. Here, we undertake a formal identification analysis to integrate conjoint analysis with the potential outcomes framework for causal inference. We propose a new causal estimand and show that it can be nonparametrically identified and easily estimated from conjoint data using a fully randomized design. We then demonstrate the value of these techniques through empirical applications to voter decision-making and attitudes toward immigrants.