A Monte Carlo Study of Tests for the Independence of Irrelevant Alternatives Property

A plethora of tests for the Independence of Irrelevant Alternatives (HA) property of Logit models of discrete choice behavior has been proposed in the literature. These tests are based upon asymptotic arguments and little is known about their size and power properties in finite samples. This paper u...

Full description

Bibliographic Details
Main Authors: Fry, T.R.L., Harris, Mark
Format: Journal Article
Language:English
Published: Elsevier Ltd 1996
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/81820
_version_ 1848764429951303680
author Fry, T.R.L.
Harris, Mark
author_facet Fry, T.R.L.
Harris, Mark
author_sort Fry, T.R.L.
building Curtin Institutional Repository
collection Online Access
description A plethora of tests for the Independence of Irrelevant Alternatives (HA) property of Logit models of discrete choice behavior has been proposed in the literature. These tests are based upon asymptotic arguments and little is known about their size and power properties in finite samples. This paper uses a Monte Carlo simulation study to investigate the size and power properties of six tests for IIA in the multinomial Logit model. Our results show that the majority of tests based upon partitioning the choice set appear to have very poor size and power properties in small samples. Tests for IIA based upon the DOGIT model, similarly have poor size properties, but in some circumstances do have reasonable power properties.
first_indexed 2025-11-14T11:19:13Z
format Journal Article
id curtin-20.500.11937-81820
institution Curtin University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T11:19:13Z
publishDate 1996
publisher Elsevier Ltd
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-818202021-03-25T02:29:31Z A Monte Carlo Study of Tests for the Independence of Irrelevant Alternatives Property Fry, T.R.L. Harris, Mark Social Sciences Science & Technology Technology Economics Engineering, Civil Operations Research & Management Science Transportation Transportation Science & Technology Business & Economics Engineering MULTINOMIAL LOGIT MODEL SPECIFICATION TESTS A plethora of tests for the Independence of Irrelevant Alternatives (HA) property of Logit models of discrete choice behavior has been proposed in the literature. These tests are based upon asymptotic arguments and little is known about their size and power properties in finite samples. This paper uses a Monte Carlo simulation study to investigate the size and power properties of six tests for IIA in the multinomial Logit model. Our results show that the majority of tests based upon partitioning the choice set appear to have very poor size and power properties in small samples. Tests for IIA based upon the DOGIT model, similarly have poor size properties, but in some circumstances do have reasonable power properties. 1996 Journal Article http://hdl.handle.net/20.500.11937/81820 10.1016/0191-2615(95)00019-4 English Elsevier Ltd restricted
spellingShingle Social Sciences
Science & Technology
Technology
Economics
Engineering, Civil
Operations Research & Management Science
Transportation
Transportation Science & Technology
Business & Economics
Engineering
MULTINOMIAL LOGIT MODEL
SPECIFICATION TESTS
Fry, T.R.L.
Harris, Mark
A Monte Carlo Study of Tests for the Independence of Irrelevant Alternatives Property
title A Monte Carlo Study of Tests for the Independence of Irrelevant Alternatives Property
title_full A Monte Carlo Study of Tests for the Independence of Irrelevant Alternatives Property
title_fullStr A Monte Carlo Study of Tests for the Independence of Irrelevant Alternatives Property
title_full_unstemmed A Monte Carlo Study of Tests for the Independence of Irrelevant Alternatives Property
title_short A Monte Carlo Study of Tests for the Independence of Irrelevant Alternatives Property
title_sort monte carlo study of tests for the independence of irrelevant alternatives property
topic Social Sciences
Science & Technology
Technology
Economics
Engineering, Civil
Operations Research & Management Science
Transportation
Transportation Science & Technology
Business & Economics
Engineering
MULTINOMIAL LOGIT MODEL
SPECIFICATION TESTS
url http://hdl.handle.net/20.500.11937/81820