The Role of Preference Axioms and Respondent Behaviour in Statistical Models for Discrete Choice

Jens Leth Hougaard, Tue Tjur, Lars Peter Østerdal

Publikation: Working paperForskning

Resumé

Discrete choice experiments are widely used in relation to healthcare. A stream of recent literature therefore aims at testing the validityof the underlying preference axioms of completeness and transitivity,and detecting other preference phenomena such as unstability, learn-ing/tiredness effects, ordering effects, dominance, etc. Unfortunatelythere seems to be some confusion about what is actually being tested,and the link between the statistical tests performed and the relevantunderlying model of respondent behaviour has not been explored inthis literature. The present paper tries to clarify the notions involvedand discuss what can be tested in a general frequency of choice frame-work and more specifically in a random utility model.
OriginalsprogEngelsk
Udgivelses stedKøbenhavn
UdgiverKøbenhavns Universitet
Antal sider17
StatusUdgivet - 2004

Emneord

  • Discrete choice experiments
  • Random utility model
  • Stated preference
  • Completeness
  • Transitivity
  • Statistical tests

Citer dette

Hougaard, Jens Leth ; Tjur, Tue ; Østerdal, Lars Peter. / The Role of Preference Axioms and Respondent Behaviour in Statistical Models for Discrete Choice. København : Københavns Universitet, 2004.
@techreport{71931540c02111db9769000ea68e967b,
title = "The Role of Preference Axioms and Respondent Behaviour in Statistical Models for Discrete Choice",
abstract = "Discrete choice experiments are widely used in relation to healthcare. A stream of recent literature therefore aims at testing the validityof the underlying preference axioms of completeness and transitivity,and detecting other preference phenomena such as unstability, learn-ing/tiredness effects, ordering effects, dominance, etc. Unfortunatelythere seems to be some confusion about what is actually being tested,and the link between the statistical tests performed and the relevantunderlying model of respondent behaviour has not been explored inthis literature. The present paper tries to clarify the notions involvedand discuss what can be tested in a general frequency of choice frame-work and more specifically in a random utility model.",
keywords = "Discrete choice experiments, Random utility model, Stated preference, Completeness, Transitivity, Statistical tests, Discrete choice experiments, Random utility model, Stated preference, Completeness, Transitivity, Statistical tests",
author = "Hougaard, {Jens Leth} and Tue Tjur and {\O}sterdal, {Lars Peter}",
year = "2004",
language = "English",
publisher = "K{\o}benhavns Universitet",
address = "Denmark",
type = "WorkingPaper",
institution = "K{\o}benhavns Universitet",

}

The Role of Preference Axioms and Respondent Behaviour in Statistical Models for Discrete Choice. / Hougaard, Jens Leth; Tjur, Tue; Østerdal, Lars Peter.

København : Københavns Universitet, 2004.

Publikation: Working paperForskning

TY - UNPB

T1 - The Role of Preference Axioms and Respondent Behaviour in Statistical Models for Discrete Choice

AU - Hougaard, Jens Leth

AU - Tjur, Tue

AU - Østerdal, Lars Peter

PY - 2004

Y1 - 2004

N2 - Discrete choice experiments are widely used in relation to healthcare. A stream of recent literature therefore aims at testing the validityof the underlying preference axioms of completeness and transitivity,and detecting other preference phenomena such as unstability, learn-ing/tiredness effects, ordering effects, dominance, etc. Unfortunatelythere seems to be some confusion about what is actually being tested,and the link between the statistical tests performed and the relevantunderlying model of respondent behaviour has not been explored inthis literature. The present paper tries to clarify the notions involvedand discuss what can be tested in a general frequency of choice frame-work and more specifically in a random utility model.

AB - Discrete choice experiments are widely used in relation to healthcare. A stream of recent literature therefore aims at testing the validityof the underlying preference axioms of completeness and transitivity,and detecting other preference phenomena such as unstability, learn-ing/tiredness effects, ordering effects, dominance, etc. Unfortunatelythere seems to be some confusion about what is actually being tested,and the link between the statistical tests performed and the relevantunderlying model of respondent behaviour has not been explored inthis literature. The present paper tries to clarify the notions involvedand discuss what can be tested in a general frequency of choice frame-work and more specifically in a random utility model.

KW - Discrete choice experiments

KW - Random utility model

KW - Stated preference

KW - Completeness

KW - Transitivity

KW - Statistical tests

KW - Discrete choice experiments

KW - Random utility model

KW - Stated preference

KW - Completeness

KW - Transitivity

KW - Statistical tests

M3 - Working paper

BT - The Role of Preference Axioms and Respondent Behaviour in Statistical Models for Discrete Choice

PB - Københavns Universitet

CY - København

ER -