Multinomial Logit Processes and Preference Discovery: Inside and Outside the Black Box

DOI10.1093/RESTUD/RDAC046MaRDI QIDQ6108948zbMATH OpenFDO

Authors Simone Cerreia-Vioglio, Fabio Maccheroni, Massimo Marinacci, Aldo Rustichini

Publication date 30 June 2023

Published in Review of Economic Studies (Search for Journal in Brave)

Copyright license Creative Commons Attribution-NonCommercial 4.0 International

Full work available at URL https://arxiv.org/abs/2004.13376, https://econpapers.repec.org/RePEc:igi:igierp:615

zbMATH Keywords

discrete choice analysisdrift diffusion modelheteroscedastic extreme value modelsLuce modelmetropolis algorithmmultinomial logit modelquantal response equilibriumrational inattention

Mathematics Subject Classification ID

Applications of statistics to psychology (62P15) Decision theory (91B06)

Abstract: We provide two characterizations, one axiomatic and the other neuro-computational, of the dependence of choice probabilities on deadlines, within the widely used softmax representation [ p_{t}left( a,A ight) =dfrac{e^{frac{uleft( a ight) }{lambda left( t ight) }+alpha left( a ight) }}{sum_{bin A}e^{frac{uleft( b ight) }{lambda left( t ight) }+alpha left( b ight) }}% ] where $p_{t}left(a,Aight)$ is the probability that alternative $a$ is selected from the set $A$ of feasible alternatives if $t$ is the time available to decide, $lambda$ is a time dependent noise parameter measuring the unit cost of information, $u$ is a time independent utility function, and $alpha$ is an alternative-specific bias that determines the initial choice probabilities reflecting prior information and memory anchoring. Our axiomatic analysis provides a behavioral foundation of softmax (also known as Multinomial Logit Model when $alpha$ is constant). Our neuro-computational derivation provides a biologically inspired algorithm that may explain the emergence of softmax in choice behavior. Jointly, the two approaches provide a thorough understanding of soft-maximization in terms of internal causes (neurophysiological mechanisms) and external effects (testable implications).

Recommendations

• A Bayesian mixed logit-probit model for multinomial choice
• Bayesian nonparametric estimation and consistency of mixed multinomial logit choice models
• Approximate inference for the multinomial logit model
• Parameter estimation in multivariate logit models with many binary choices
• scientific article; zbMATH DE number 2061671
• Multinomial logit models with implicit variable selection
• scientific article; zbMATH DE number 1990011

Cited in

(1)

• A characterization of the Luce choice rule for an arbitrary collection of menus

This page was built for publication: Multinomial Logit Processes and Preference Discovery: Inside and Outside the Black Box

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6108948)