A Bayesian Vector Multidimensional Scaling Procedure Incorporating Dimension Reparameterization with Variable Selection

Duncan K.H. Fong, Wayne S. DeSarbo, Zhe Chen, Zhuying Xu

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

We propose a two-way Bayesian vector spatial procedure incorporating dimension reparameterization with a variable selection option to determine the dimensionality and simultaneously identify the significant covariates that help interpret the derived dimensions in the joint space map. We discuss how we solve identifiability problems in a Bayesian context that are associated with the two-way vector spatial model, and demonstrate through a simulation study how our proposed model outperforms a popular benchmark model. In addition, an empirical application dealing with consumers’ ratings of large sport utility vehicles is presented to illustrate the proposed methodology. We are able to obtain interpretable and managerially insightful results from our proposed model with variable selection in comparison with the benchmark model.

Original languageEnglish (US)
Pages (from-to)1043-1065
Number of pages23
JournalPsychometrika
Volume80
Issue number4
DOIs
StatePublished - Dec 1 2015

Fingerprint

Benchmarking
Reparameterization
Variable Selection
Scaling
Sports
Joints
Benchmark
Identifiability
Spatial Model
Model
Dimensionality
Covariates
Simulation Study
Methodology
Demonstrate

All Science Journal Classification (ASJC) codes

  • Psychology(all)
  • Applied Mathematics

Cite this

@article{b783b27a4dc442b196bac9c9bb64728d,
title = "A Bayesian Vector Multidimensional Scaling Procedure Incorporating Dimension Reparameterization with Variable Selection",
abstract = "We propose a two-way Bayesian vector spatial procedure incorporating dimension reparameterization with a variable selection option to determine the dimensionality and simultaneously identify the significant covariates that help interpret the derived dimensions in the joint space map. We discuss how we solve identifiability problems in a Bayesian context that are associated with the two-way vector spatial model, and demonstrate through a simulation study how our proposed model outperforms a popular benchmark model. In addition, an empirical application dealing with consumers’ ratings of large sport utility vehicles is presented to illustrate the proposed methodology. We are able to obtain interpretable and managerially insightful results from our proposed model with variable selection in comparison with the benchmark model.",
author = "Fong, {Duncan K.H.} and DeSarbo, {Wayne S.} and Zhe Chen and Zhuying Xu",
year = "2015",
month = "12",
day = "1",
doi = "10.1007/s11336-015-9449-x",
language = "English (US)",
volume = "80",
pages = "1043--1065",
journal = "Psychometrika",
issn = "0033-3123",
publisher = "Springer New York",
number = "4",

}

A Bayesian Vector Multidimensional Scaling Procedure Incorporating Dimension Reparameterization with Variable Selection. / Fong, Duncan K.H.; DeSarbo, Wayne S.; Chen, Zhe; Xu, Zhuying.

In: Psychometrika, Vol. 80, No. 4, 01.12.2015, p. 1043-1065.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Bayesian Vector Multidimensional Scaling Procedure Incorporating Dimension Reparameterization with Variable Selection

AU - Fong, Duncan K.H.

AU - DeSarbo, Wayne S.

AU - Chen, Zhe

AU - Xu, Zhuying

PY - 2015/12/1

Y1 - 2015/12/1

N2 - We propose a two-way Bayesian vector spatial procedure incorporating dimension reparameterization with a variable selection option to determine the dimensionality and simultaneously identify the significant covariates that help interpret the derived dimensions in the joint space map. We discuss how we solve identifiability problems in a Bayesian context that are associated with the two-way vector spatial model, and demonstrate through a simulation study how our proposed model outperforms a popular benchmark model. In addition, an empirical application dealing with consumers’ ratings of large sport utility vehicles is presented to illustrate the proposed methodology. We are able to obtain interpretable and managerially insightful results from our proposed model with variable selection in comparison with the benchmark model.

AB - We propose a two-way Bayesian vector spatial procedure incorporating dimension reparameterization with a variable selection option to determine the dimensionality and simultaneously identify the significant covariates that help interpret the derived dimensions in the joint space map. We discuss how we solve identifiability problems in a Bayesian context that are associated with the two-way vector spatial model, and demonstrate through a simulation study how our proposed model outperforms a popular benchmark model. In addition, an empirical application dealing with consumers’ ratings of large sport utility vehicles is presented to illustrate the proposed methodology. We are able to obtain interpretable and managerially insightful results from our proposed model with variable selection in comparison with the benchmark model.

UR - http://www.scopus.com/inward/record.url?scp=84947125898&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84947125898&partnerID=8YFLogxK

U2 - 10.1007/s11336-015-9449-x

DO - 10.1007/s11336-015-9449-x

M3 - Article

C2 - 25733494

AN - SCOPUS:84947125898

VL - 80

SP - 1043

EP - 1065

JO - Psychometrika

JF - Psychometrika

SN - 0033-3123

IS - 4

ER -