An exponential-family multidimensional scaling mixture methodology

Michel Wedel, Wayne Desarbo

Research output: Contribution to journalArticle

32 Citations (Scopus)

Abstract

A multidimensional scaling methodology (STUNMIX) for the analysis of subjects’ preference/choice of stimuli that sets out to integrate the previous work in this area into a single framework, as well as to provide a variety of new options and models, is presented. Locations of the stimuli and the ideal points of derived segments of subjects on latent dimensions are estimated simultaneously. The methodology is formulated in the framework of the exponential family of distributions, whereby a wide range of different data types can be analyzed. Possible reparameterizations of stimulus coordinates by stimulus characteristics, as well as of probabilities of segment membership by subject background variables, are permitted. The models are estimated in a maximum likelihood framework. The performance of the models is demonstrated on synthetic data, and robustness is investigated. An empirical application is provided, concerning intentions to buy portable telephones.

Original languageEnglish (US)
Pages (from-to)447-459
Number of pages13
JournalJournal of Business and Economic Statistics
Volume14
Issue number4
DOIs
StatePublished - Jan 1 1996

Fingerprint

multidimensional scaling
Exponential Family
stimulus
Scaling
Methodology
methodology
Reparameterization
Synthetic Data
Maximum Likelihood
Integrate
Model
Robustness
telephone
Range of data
Framework
Exponential family
Multidimensional scaling
performance

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Social Sciences (miscellaneous)
  • Economics and Econometrics
  • Statistics, Probability and Uncertainty

Cite this

Wedel, Michel ; Desarbo, Wayne. / An exponential-family multidimensional scaling mixture methodology. In: Journal of Business and Economic Statistics. 1996 ; Vol. 14, No. 4. pp. 447-459.
@article{cd30528d1eb34e2793e7c7dd18623b4e,
title = "An exponential-family multidimensional scaling mixture methodology",
abstract = "A multidimensional scaling methodology (STUNMIX) for the analysis of subjects’ preference/choice of stimuli that sets out to integrate the previous work in this area into a single framework, as well as to provide a variety of new options and models, is presented. Locations of the stimuli and the ideal points of derived segments of subjects on latent dimensions are estimated simultaneously. The methodology is formulated in the framework of the exponential family of distributions, whereby a wide range of different data types can be analyzed. Possible reparameterizations of stimulus coordinates by stimulus characteristics, as well as of probabilities of segment membership by subject background variables, are permitted. The models are estimated in a maximum likelihood framework. The performance of the models is demonstrated on synthetic data, and robustness is investigated. An empirical application is provided, concerning intentions to buy portable telephones.",
author = "Michel Wedel and Wayne Desarbo",
year = "1996",
month = "1",
day = "1",
doi = "10.1080/07350015.1996.10524674",
language = "English (US)",
volume = "14",
pages = "447--459",
journal = "Journal of Business and Economic Statistics",
issn = "0735-0015",
publisher = "American Statistical Association",
number = "4",

}

An exponential-family multidimensional scaling mixture methodology. / Wedel, Michel; Desarbo, Wayne.

In: Journal of Business and Economic Statistics, Vol. 14, No. 4, 01.01.1996, p. 447-459.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An exponential-family multidimensional scaling mixture methodology

AU - Wedel, Michel

AU - Desarbo, Wayne

PY - 1996/1/1

Y1 - 1996/1/1

N2 - A multidimensional scaling methodology (STUNMIX) for the analysis of subjects’ preference/choice of stimuli that sets out to integrate the previous work in this area into a single framework, as well as to provide a variety of new options and models, is presented. Locations of the stimuli and the ideal points of derived segments of subjects on latent dimensions are estimated simultaneously. The methodology is formulated in the framework of the exponential family of distributions, whereby a wide range of different data types can be analyzed. Possible reparameterizations of stimulus coordinates by stimulus characteristics, as well as of probabilities of segment membership by subject background variables, are permitted. The models are estimated in a maximum likelihood framework. The performance of the models is demonstrated on synthetic data, and robustness is investigated. An empirical application is provided, concerning intentions to buy portable telephones.

AB - A multidimensional scaling methodology (STUNMIX) for the analysis of subjects’ preference/choice of stimuli that sets out to integrate the previous work in this area into a single framework, as well as to provide a variety of new options and models, is presented. Locations of the stimuli and the ideal points of derived segments of subjects on latent dimensions are estimated simultaneously. The methodology is formulated in the framework of the exponential family of distributions, whereby a wide range of different data types can be analyzed. Possible reparameterizations of stimulus coordinates by stimulus characteristics, as well as of probabilities of segment membership by subject background variables, are permitted. The models are estimated in a maximum likelihood framework. The performance of the models is demonstrated on synthetic data, and robustness is investigated. An empirical application is provided, concerning intentions to buy portable telephones.

UR - http://www.scopus.com/inward/record.url?scp=0030491631&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030491631&partnerID=8YFLogxK

U2 - 10.1080/07350015.1996.10524674

DO - 10.1080/07350015.1996.10524674

M3 - Article

AN - SCOPUS:0030491631

VL - 14

SP - 447

EP - 459

JO - Journal of Business and Economic Statistics

JF - Journal of Business and Economic Statistics

SN - 0735-0015

IS - 4

ER -