On the Distributional Robustness of Finite Rational Inattention Models

TL;DR

This paper analyzes how decision makers using rational inattention models can achieve robustness against uncertainty in prior distributions, providing a tractable way to characterize and quantify the impact of prior ambiguity.

Contribution

It introduces a full characterization of distributional robustness in rational inattention models via a concave program and defines the concept of Worst-Case Sensitivity.

Findings

Characterization of robust consideration sets

Necessary and sufficient conditions for robustness

Quantification of prior uncertainty impact

Abstract

In this paper we study a rational inattention model in environments where the decision maker faces uncertainty about the true prior distribution over states. The decision maker seeks to select a stochastic choice rule over a finite set of alternatives that is robust to prior ambiguity. We fully characterize the distributional robustness of the rational inattention model in terms of a tractable concave program. We establish necessary and sufficient conditions to construct robust consideration sets. Finally, we quantify the impact of prior uncertainty, by introducing the notion of \emph{Worst-Case Sensitivity}.