A Random Attention and Utility Model

TL;DR

This paper extends the stochastic revealed preference methodology to models with limited consideration, introducing nonparametric tests and conditions that encompass a broad class of consideration models with heterogeneous preferences.

Contribution

It generalizes existing models by incorporating limited consideration, providing a nonparametric framework with testable restrictions and broad applicability.

Findings

Framework allows statistical testing of limited consideration models.

Imposes monotonicity and stability conditions for identification.

Extends parametric consideration models to nonparametric settings.

Abstract

We generalize the stochastic revealed preference methodology of McFadden and Richter (1990) for finite choice sets to settings with limited consideration. Our approach is nonparametric and requires partial choice set variation. We impose a monotonicity condition on attention first proposed by Cattaneo et al. (2020) and a stability condition on the marginal distribution of preferences. Our framework is amenable to statistical testing. These new restrictions extend widely known parametric models of consideration with heterogeneous preferences.