How to detect heterogeneity in conjoint experiments

Conjoint experiments are fast becoming one of the dominant experimental methods within the social sciences. Despite recent efforts to model heterogeneity within this type of experiment, the relationship between the conjoint design and lower-level causal estimands is underdeveloped. In this article, we clarify how conjoint heterogeneity can be construed as a set of nested, causal parameters that correspond to the levels of the conjoint design. We then use this framework to propose a new estimation strategy, using machine learning, that better allows researchers to evaluate treatment effect heterogeneity. We also provide novel tools for classifying and analyzing heterogeneity postestimation using partitioning algorithms. Replicating two conjoint experiments, we demonstrate our theoretical argument and show how this method helps estimate and detect substantive patterns of heterogeneity. To accompany this article, we provide new a R package, cjbart, that allows researchers to model heterogeneity in their experimental conjoint data.