Bias caused by omitted variables in random regret choice models: Formal and empirical analysis of orthogonal design data

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Citation (Scopus)

Abstract

The aim of this study is to explore the bias caused by omitted variables in both random utility and random regret models. Since the behavioural underpinnings of these models differ, the bias is also expected to differ. We focus our analysis on stated choice data, based on orthogonal fractional factorial experimental designs, because the endogeneity, defined as a correlation between selected and omitted explanatory variables is a nonissue in such data. We will show that while the bias caused by omitted variables in the random utility model can be simply neutralised by using alternative specific constants, it still exists in the random regret model because the bias in this type of choice models depends on the attribute dominance structure in the data and thus is not constant.

Original languageEnglish
Title of host publicationProceedings of the 21st International Conference of Hong Kong Society for Transportation Studies, HKSTS 2016 - Smart Transportation
EditorsA.W.G. Wong, S.H.F. Wong, G.L.M. Leung
Place of PublicationHong Kong
PublisherHong Kong Society for Transportation Studies
Pages261-267
Number of pages7
ISBN (Electronic)9789881581457
Publication statusPublished - 2016
Event21st International Conference of Hong Kong Society for Transportation Studies (HKSTS 2016) - Hong Kong, Hong Kong
Duration: 10 Dec 201612 Dec 2016
http://www.hksts.org/conf16.htm

Conference

Conference21st International Conference of Hong Kong Society for Transportation Studies (HKSTS 2016)
Abbreviated titleHKSTS
CountryHong Kong
CityHong Kong
Period10/12/1612/12/16
OtherSmart Transportation
Internet address

Fingerprint

trend
Design of experiments

Keywords

  • Omitted variables
  • Regret minimization
  • Utility maximization

Cite this

Jang, S., Rasouli, S., & Timmermans, H. J. P. (2016). Bias caused by omitted variables in random regret choice models: Formal and empirical analysis of orthogonal design data. In A. W. G. Wong, S. H. F. Wong, & G. L. M. Leung (Eds.), Proceedings of the 21st International Conference of Hong Kong Society for Transportation Studies, HKSTS 2016 - Smart Transportation (pp. 261-267). Hong Kong: Hong Kong Society for Transportation Studies.
Jang, S. ; Rasouli, S. ; Timmermans, H. J.P. / Bias caused by omitted variables in random regret choice models : Formal and empirical analysis of orthogonal design data. Proceedings of the 21st International Conference of Hong Kong Society for Transportation Studies, HKSTS 2016 - Smart Transportation. editor / A.W.G. Wong ; S.H.F. Wong ; G.L.M. Leung. Hong Kong : Hong Kong Society for Transportation Studies, 2016. pp. 261-267
@inproceedings{d59a5791bf434012a54a1c2e619d81fa,
title = "Bias caused by omitted variables in random regret choice models: Formal and empirical analysis of orthogonal design data",
abstract = "The aim of this study is to explore the bias caused by omitted variables in both random utility and random regret models. Since the behavioural underpinnings of these models differ, the bias is also expected to differ. We focus our analysis on stated choice data, based on orthogonal fractional factorial experimental designs, because the endogeneity, defined as a correlation between selected and omitted explanatory variables is a nonissue in such data. We will show that while the bias caused by omitted variables in the random utility model can be simply neutralised by using alternative specific constants, it still exists in the random regret model because the bias in this type of choice models depends on the attribute dominance structure in the data and thus is not constant.",
keywords = "Omitted variables, Regret minimization, Utility maximization",
author = "S. Jang and S. Rasouli and Timmermans, {H. J.P.}",
year = "2016",
language = "English",
pages = "261--267",
editor = "A.W.G. Wong and S.H.F. Wong and G.L.M. Leung",
booktitle = "Proceedings of the 21st International Conference of Hong Kong Society for Transportation Studies, HKSTS 2016 - Smart Transportation",
publisher = "Hong Kong Society for Transportation Studies",

}

Jang, S, Rasouli, S & Timmermans, HJP 2016, Bias caused by omitted variables in random regret choice models: Formal and empirical analysis of orthogonal design data. in AWG Wong, SHF Wong & GLM Leung (eds), Proceedings of the 21st International Conference of Hong Kong Society for Transportation Studies, HKSTS 2016 - Smart Transportation. Hong Kong Society for Transportation Studies, Hong Kong, pp. 261-267, 21st International Conference of Hong Kong Society for Transportation Studies (HKSTS 2016), Hong Kong, Hong Kong, 10/12/16.

Bias caused by omitted variables in random regret choice models : Formal and empirical analysis of orthogonal design data. / Jang, S.; Rasouli, S.; Timmermans, H. J.P.

Proceedings of the 21st International Conference of Hong Kong Society for Transportation Studies, HKSTS 2016 - Smart Transportation. ed. / A.W.G. Wong; S.H.F. Wong; G.L.M. Leung. Hong Kong : Hong Kong Society for Transportation Studies, 2016. p. 261-267.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Bias caused by omitted variables in random regret choice models

T2 - Formal and empirical analysis of orthogonal design data

AU - Jang, S.

AU - Rasouli, S.

AU - Timmermans, H. J.P.

PY - 2016

Y1 - 2016

N2 - The aim of this study is to explore the bias caused by omitted variables in both random utility and random regret models. Since the behavioural underpinnings of these models differ, the bias is also expected to differ. We focus our analysis on stated choice data, based on orthogonal fractional factorial experimental designs, because the endogeneity, defined as a correlation between selected and omitted explanatory variables is a nonissue in such data. We will show that while the bias caused by omitted variables in the random utility model can be simply neutralised by using alternative specific constants, it still exists in the random regret model because the bias in this type of choice models depends on the attribute dominance structure in the data and thus is not constant.

AB - The aim of this study is to explore the bias caused by omitted variables in both random utility and random regret models. Since the behavioural underpinnings of these models differ, the bias is also expected to differ. We focus our analysis on stated choice data, based on orthogonal fractional factorial experimental designs, because the endogeneity, defined as a correlation between selected and omitted explanatory variables is a nonissue in such data. We will show that while the bias caused by omitted variables in the random utility model can be simply neutralised by using alternative specific constants, it still exists in the random regret model because the bias in this type of choice models depends on the attribute dominance structure in the data and thus is not constant.

KW - Omitted variables

KW - Regret minimization

KW - Utility maximization

UR - http://www.scopus.com/inward/record.url?scp=85050589950&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85050589950

SP - 261

EP - 267

BT - Proceedings of the 21st International Conference of Hong Kong Society for Transportation Studies, HKSTS 2016 - Smart Transportation

A2 - Wong, A.W.G.

A2 - Wong, S.H.F.

A2 - Leung, G.L.M.

PB - Hong Kong Society for Transportation Studies

CY - Hong Kong

ER -

Jang S, Rasouli S, Timmermans HJP. Bias caused by omitted variables in random regret choice models: Formal and empirical analysis of orthogonal design data. In Wong AWG, Wong SHF, Leung GLM, editors, Proceedings of the 21st International Conference of Hong Kong Society for Transportation Studies, HKSTS 2016 - Smart Transportation. Hong Kong: Hong Kong Society for Transportation Studies. 2016. p. 261-267