Behavioral Foundations of Nested Stochastic Choice and Nested Logit

36 Pages Posted: 17 Aug 2019

See all articles by Matthew Kovach

Matthew Kovach

Virginia Polytechnic Institute & State University - Department of Economics

Gerelt Tserenjigmid

Virginia Polytechnic Institute & State University

Date Written: August 5, 2019

Abstract

We introduce a stochastic choice model, Nested Stochastic Choice (NSC), which generalizes nested logit. NSC features a “two-step” Luce procedure: a nest (subset) is chosen by one Luce formula and an alternative is chosen from that nest by another Luce formula. We characterize NSC with a single axiom, Independence of Symmetric Alternatives, which relaxes Luce’s IIA based on revealed similarity. We identify a key behavioral feature of nested logit — nest probability is increasing in the sum of utilities — and characterize nested logit and the Extended Nested Logit (ENL): nested logit without functional form assumptions.

Keywords: Nested Stochastic Choice, Luce Model, Nested Logit, IIA, Similarity Effect, Regularity, Revealed Similarity

JEL Classification: D01, D81, D9

Suggested Citation

Kovach, Matthew and Tserenjigmid, Gerelt, Behavioral Foundations of Nested Stochastic Choice and Nested Logit (August 5, 2019). Available at SSRN: https://ssrn.com/abstract=3437165 or http://dx.doi.org/10.2139/ssrn.3437165

Matthew Kovach (Contact Author)

Virginia Polytechnic Institute & State University - Department of Economics ( email )

3016 Pamplin Hall (0316)
880 West Campus Drive
Blacksburg, VA 24061
United States

Gerelt Tserenjigmid

Virginia Polytechnic Institute & State University ( email )

Blacksburg, VA 24061
United States

Register to save articles to
your library

Register

Paper statistics

Downloads
11
Abstract Views
69
PlumX Metrics