Applied Seminar

Stephane Bonhomme

University of Chicago


A1/1-61P – 14:30


We study empirical decision rules that depend not only on current covariates, but also on the process of covariates. We obtain those as the nonparametric reduced forms of structural dynamic models of individual choice, where the process of covariates governs the individual’s expectations about future values. We describe two strategies to identify and estimate decision rules: one that requires the availability of subjective expectations data, and another one that relies on the assumption that individuals have rational beliefs. We use our approach to estimate the impact of a change in the covariates’ process on decisions and other outcomes. We decompose the total impact of such a change into a contemporaneous effect and a dynamic effect accounting for expectations. We illustrateour approach in two settings. In a model of consumption and saving, we show how to estimate the effects on consumption decisions of a change in the income process. In a model of agricultural production, we show how to estimate the impact of changes in today’s weather and expectations about tomorrow’s weather, thus accounting for the possibility of adaptation

Leave Comment

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>

clear formSubmit

This site uses Akismet to reduce spam. Learn how your comment data is processed.