A Bayesian analysis of the multinomial probit model with fully identified parameters

Robert McCulloch, Nicholas G. Polson, Peter E. Rossi

Research output: Contribution to journalArticle

137 Citations (Scopus)

Abstract

We present a new prior and corresponding algorithm for Bayesian analysis of the multinomial probit model. Our new approach places a prior directly on the identified parameter space. The key is the specification of a prior on the covariance matrix so that the (1,1) element if fixed at 1 and it is possible to draw from the posterior using standard distributions. Analytical results are derived which can be used to aid in assessment of the prior.

Original languageEnglish (US)
Pages (from-to)173-193
Number of pages21
JournalJournal of Econometrics
Volume99
Issue number1
StatePublished - Nov 2000
Externally publishedYes

Fingerprint

Multinomial Model
Probit Model
Bayesian Analysis
Covariance matrix
Parameter Space
Specification
Standards
Multinomial probit model
Bayesian analysis

Keywords

  • Bayesian analysis
  • Priors
  • Probit models

ASJC Scopus subject areas

  • Economics and Econometrics
  • Finance
  • Statistics and Probability

Cite this

A Bayesian analysis of the multinomial probit model with fully identified parameters. / McCulloch, Robert; Polson, Nicholas G.; Rossi, Peter E.

In: Journal of Econometrics, Vol. 99, No. 1, 11.2000, p. 173-193.

Research output: Contribution to journalArticle

McCulloch, Robert ; Polson, Nicholas G. ; Rossi, Peter E. / A Bayesian analysis of the multinomial probit model with fully identified parameters. In: Journal of Econometrics. 2000 ; Vol. 99, No. 1. pp. 173-193.
@article{99b018b86d3b42a3b1e4d8e2e17054ee,
title = "A Bayesian analysis of the multinomial probit model with fully identified parameters",
abstract = "We present a new prior and corresponding algorithm for Bayesian analysis of the multinomial probit model. Our new approach places a prior directly on the identified parameter space. The key is the specification of a prior on the covariance matrix so that the (1,1) element if fixed at 1 and it is possible to draw from the posterior using standard distributions. Analytical results are derived which can be used to aid in assessment of the prior.",
keywords = "Bayesian analysis, Priors, Probit models",
author = "Robert McCulloch and Polson, {Nicholas G.} and Rossi, {Peter E.}",
year = "2000",
month = "11",
language = "English (US)",
volume = "99",
pages = "173--193",
journal = "Journal of Econometrics",
issn = "0304-4076",
publisher = "Elsevier BV",
number = "1",

}

TY - JOUR

T1 - A Bayesian analysis of the multinomial probit model with fully identified parameters

AU - McCulloch, Robert

AU - Polson, Nicholas G.

AU - Rossi, Peter E.

PY - 2000/11

Y1 - 2000/11

N2 - We present a new prior and corresponding algorithm for Bayesian analysis of the multinomial probit model. Our new approach places a prior directly on the identified parameter space. The key is the specification of a prior on the covariance matrix so that the (1,1) element if fixed at 1 and it is possible to draw from the posterior using standard distributions. Analytical results are derived which can be used to aid in assessment of the prior.

AB - We present a new prior and corresponding algorithm for Bayesian analysis of the multinomial probit model. Our new approach places a prior directly on the identified parameter space. The key is the specification of a prior on the covariance matrix so that the (1,1) element if fixed at 1 and it is possible to draw from the posterior using standard distributions. Analytical results are derived which can be used to aid in assessment of the prior.

KW - Bayesian analysis

KW - Priors

KW - Probit models

UR - http://www.scopus.com/inward/record.url?scp=0001434493&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0001434493&partnerID=8YFLogxK

M3 - Article

VL - 99

SP - 173

EP - 193

JO - Journal of Econometrics

JF - Journal of Econometrics

SN - 0304-4076

IS - 1

ER -