Testing for Essential Heterogeneity∗

This paper examines the properties of instrumental variables (IV) applied to models with essential heterogeneity, that is, models where responses to interventions are heterogeneous and agents adopt treatments (participate in programs) with at least partial knowledge of their idiosyncratic response. We present several empirical examples demonstrating the importance of unobserved heterogeneity in economic applications. For each empirical example we implement a simple test for the presence of essential heterogeneity, we compare the IV estimates with other treatment parameters, and we analyze whether or not IV can be used to provide meaningful answers to well-posed economic questions.