Efficient Bayesian analysis of multivariate aggregate choices

Taeyoung Park, Seonghyun Jeong

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

In estimating individual choice behaviour using multivariate aggregate choice data, the method of data augmentation requires the imputation of individual choices given their partial sums. This article proposes and develops an efficient procedure of simulating multivariate individual choices given their aggregate sums, capitalizing on a sequence of auxiliary distributions. In this framework, a joint distribution of multiple binary vectors given their sums is approximated as a sequence of conditional Bernoulli distributions. The proposed approach is evaluated through a simulation study and is applied to a political science study.

Original languageEnglish
Pages (from-to)3352-3366
Number of pages15
JournalJournal of Statistical Computation and Simulation
Volume85
Issue number16
DOIs
Publication statusPublished - 2015 Nov 2

Fingerprint

Bayesian Analysis
Data Augmentation
Imputation
Partial Sums
Bernoulli
Joint Distribution
Simulation Study
Binary
Bayesian analysis
Framework
Simulation study
Science studies
Joint distribution
Conditional distribution
Data augmentation
Choice behavior
Political Science

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Modelling and Simulation
  • Statistics, Probability and Uncertainty
  • Applied Mathematics

Cite this

@article{5a8c9479471740cfbdc9a53b39d3c8ae,
title = "Efficient Bayesian analysis of multivariate aggregate choices",
abstract = "In estimating individual choice behaviour using multivariate aggregate choice data, the method of data augmentation requires the imputation of individual choices given their partial sums. This article proposes and develops an efficient procedure of simulating multivariate individual choices given their aggregate sums, capitalizing on a sequence of auxiliary distributions. In this framework, a joint distribution of multiple binary vectors given their sums is approximated as a sequence of conditional Bernoulli distributions. The proposed approach is evaluated through a simulation study and is applied to a political science study.",
author = "Taeyoung Park and Seonghyun Jeong",
year = "2015",
month = "11",
day = "2",
doi = "10.1080/00949655.2014.973411",
language = "English",
volume = "85",
pages = "3352--3366",
journal = "Journal of Statistical Computation and Simulation",
issn = "0094-9655",
publisher = "Taylor and Francis Ltd.",
number = "16",

}

Efficient Bayesian analysis of multivariate aggregate choices. / Park, Taeyoung; Jeong, Seonghyun.

In: Journal of Statistical Computation and Simulation, Vol. 85, No. 16, 02.11.2015, p. 3352-3366.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Efficient Bayesian analysis of multivariate aggregate choices

AU - Park, Taeyoung

AU - Jeong, Seonghyun

PY - 2015/11/2

Y1 - 2015/11/2

N2 - In estimating individual choice behaviour using multivariate aggregate choice data, the method of data augmentation requires the imputation of individual choices given their partial sums. This article proposes and develops an efficient procedure of simulating multivariate individual choices given their aggregate sums, capitalizing on a sequence of auxiliary distributions. In this framework, a joint distribution of multiple binary vectors given their sums is approximated as a sequence of conditional Bernoulli distributions. The proposed approach is evaluated through a simulation study and is applied to a political science study.

AB - In estimating individual choice behaviour using multivariate aggregate choice data, the method of data augmentation requires the imputation of individual choices given their partial sums. This article proposes and develops an efficient procedure of simulating multivariate individual choices given their aggregate sums, capitalizing on a sequence of auxiliary distributions. In this framework, a joint distribution of multiple binary vectors given their sums is approximated as a sequence of conditional Bernoulli distributions. The proposed approach is evaluated through a simulation study and is applied to a political science study.

UR - http://www.scopus.com/inward/record.url?scp=84939265010&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84939265010&partnerID=8YFLogxK

U2 - 10.1080/00949655.2014.973411

DO - 10.1080/00949655.2014.973411

M3 - Article

AN - SCOPUS:84939265010

VL - 85

SP - 3352

EP - 3366

JO - Journal of Statistical Computation and Simulation

JF - Journal of Statistical Computation and Simulation

SN - 0094-9655

IS - 16

ER -