Non-Linear Mixed Logit

Steffen Andersen, Glenn W. Harrison, Arne Risa Hole, Morten Lau, E. Elisabet Rutström

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

We develop an extension of the familiar linear mixed logit model to allow for the direct estimation of parametric non-linear functions defined over structural parameters. Classic applications include the estimation of coefficients of utility functions to characterize risk attitudes and discounting functions to characterize impatience. There are several unexpected benefits of this extension, apart from the ability to directly estimate structural parameters of theoretical interest.
We develop an extension of the familiar linear mixed logit model to allow for the direct estimation of parametric non-linear functions defined over structural parameters. Classic applications include the estimation of coefficients of utility functions to characterize risk attitudes and discounting functions to characterize impatience. There are several unexpected benefits of this extension, apart from the ability to directly estimate structural parameters of theoretical interest.
LanguageEnglish
JournalTheory and Decision
Volume73
Issue number1
Pages77-96
Number of pages20
ISSN0040-5833
DOIs
StatePublished - Jul 2012

Keywords

  • Risk Attitudes
  • Random Coefficients
  • Mixed Logit
  • Lottery Choices
  • Behavioral Econometrics
  • Structural Estimation

Cite this

Andersen, S., Harrison, G. W., Hole, A. R., Lau, M., & Rutström, E. E. (2012). Non-Linear Mixed Logit. Theory and Decision, 73(1), 77-96. DOI: 10.1007/s11238-011-9277-0
Andersen, Steffen ; Harrison, Glenn W. ; Hole, Arne Risa ; Lau, Morten ; Rutström, E. Elisabet. / Non-Linear Mixed Logit. In: Theory and Decision. 2012 ; Vol. 73, No. 1. pp. 77-96
@article{9961a282f2ca47e786ce3977b2dceba1,
title = "Non-Linear Mixed Logit",
abstract = "We develop an extension of the familiar linear mixed logit model to allow for the direct estimation of parametric non-linear functions defined over structural parameters. Classic applications include the estimation of coefficients of utility functions to characterize risk attitudes and discounting functions to characterize impatience. There are several unexpected benefits of this extension, apart from the ability to directly estimate structural parameters of theoretical interest.",
keywords = "Risk Attitudes, Random Coefficients, Mixed Logit, Lottery Choices, Behavioral Econometrics, Structural Estimation",
author = "Steffen Andersen and Harrison, {Glenn W.} and Hole, {Arne Risa} and Morten Lau and Rutstr{\"o}m, {E. Elisabet}",
note = "Published online: 14 July 2011",
year = "2012",
month = "7",
doi = "10.1007/s11238-011-9277-0",
language = "English",
volume = "73",
pages = "77--96",
journal = "Theory and Decision",
issn = "0040-5833",
publisher = "Springer",
number = "1",

}

Andersen, S, Harrison, GW, Hole, AR, Lau, M & Rutström, EE 2012, 'Non-Linear Mixed Logit' Theory and Decision, vol. 73, no. 1, pp. 77-96. DOI: 10.1007/s11238-011-9277-0

Non-Linear Mixed Logit. / Andersen, Steffen; Harrison, Glenn W.; Hole, Arne Risa; Lau, Morten; Rutström, E. Elisabet.

In: Theory and Decision, Vol. 73, No. 1, 07.2012, p. 77-96.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Non-Linear Mixed Logit

AU - Andersen,Steffen

AU - Harrison,Glenn W.

AU - Hole,Arne Risa

AU - Lau,Morten

AU - Rutström,E. Elisabet

N1 - Published online: 14 July 2011

PY - 2012/7

Y1 - 2012/7

N2 - We develop an extension of the familiar linear mixed logit model to allow for the direct estimation of parametric non-linear functions defined over structural parameters. Classic applications include the estimation of coefficients of utility functions to characterize risk attitudes and discounting functions to characterize impatience. There are several unexpected benefits of this extension, apart from the ability to directly estimate structural parameters of theoretical interest.

AB - We develop an extension of the familiar linear mixed logit model to allow for the direct estimation of parametric non-linear functions defined over structural parameters. Classic applications include the estimation of coefficients of utility functions to characterize risk attitudes and discounting functions to characterize impatience. There are several unexpected benefits of this extension, apart from the ability to directly estimate structural parameters of theoretical interest.

KW - Risk Attitudes

KW - Random Coefficients

KW - Mixed Logit

KW - Lottery Choices

KW - Behavioral Econometrics

KW - Structural Estimation

U2 - 10.1007/s11238-011-9277-0

DO - 10.1007/s11238-011-9277-0

M3 - Journal article

VL - 73

SP - 77

EP - 96

JO - Theory and Decision

T2 - Theory and Decision

JF - Theory and Decision

SN - 0040-5833

IS - 1

ER -

Andersen S, Harrison GW, Hole AR, Lau M, Rutström EE. Non-Linear Mixed Logit. Theory and Decision. 2012 Jul;73(1):77-96. Available from, DOI: 10.1007/s11238-011-9277-0