Recovering utility

TL;DR

This paper establishes conditions under which a utility function can be recovered from finite choice data, applicable to modern decision theories, including noisy environments, emphasizing the importance of a monetary context for identification.

Contribution

It provides a general recoverability result for utility functions from choice data, extending to models with noise and various utility parametrizations.

Findings

Utility functions are recoverable under certain conditions in choice experiments.

Monotonicity in monetary environments is key for identification.

Recovery is possible even with noise and deviations from utility maximization.

Abstract

We provide sufficient conditions under which a utility function may be recovered from a finite choice experiment. Identification, as is commonly understood in decision theory, is not enough. We provide a general recoverability result that is widely applicable to modern theories of choice under uncertainty. Key is to allow for a monetary environment, in which an objective notion of monotonicity is meaningful. In such environments, we show that subjective expected utility, as well as variational preferences, and other parametrizations of utilities over uncertain acts are recoverable. We also consider utility recovery in a statistical model with noise and random deviations from utility maximization.