Recovering Preferences from Finite Data

TL;DR

This paper establishes conditions under which preferences estimated from limited data converge to a true underlying preference, unifying traditional revealed preference models with error-inclusive approaches across various economic contexts.

Contribution

It introduces weak conditions for preference convergence from finite data, applicable to multiple economic decision-making scenarios, bridging revealed preferences and error-tolerant models.

Findings

Conditions for preference convergence are broadly applicable.

Framework unifies revealed preferences with models allowing errors.

Validates convergence in diverse economic environments.

Abstract

We study preferences estimated from finite choice experiments and provide sufficient conditions for convergence to a unique underlying "true" preference. Our conditions are weak, and therefore valid in a wide range of economic environments. We develop applications to expected utility theory, choice over consumption bundles, menu choice and intertemporal consumption. Our framework unifies the revealed preference tradition with models that allow for errors.