Three-way metric unfolding via alternating weighted least squares

Wayne Desarbo, J. Douglas Carroll

Research output: Contribution to journalArticle

47 Citations (Scopus)

Abstract

Three-way unfolding was developed by DeSarbo (1978) and reported in DeSarbo and Carroll (1980, 1981) as a new model to accommodate the analysis of two-mode three-way data (e.g., nonsymmetric proximities for stimulus objects collected over time) and three-mode, three-way data (e.g., subjects rendering preference judgments for various stimuli in different usage occasions or situations). This paper presents a revised objective function and new algorithm which attempt to prevent the common type of degenerate solutions encountered in typical unfolding analysis. We begin with an introduction of the problem and a review of three-way unfolding. The three-way unfolding model, weighted objective function, and new algorithm are presented. Monte Carlo work via a fractional factorial experimental design is described investigating the effect of several data and model factors on overall algorithm performance. Finally, three applications of the methodology are reported illustrating the flexibility and robustness of the procedure.

Original languageEnglish (US)
Pages (from-to)275-300
Number of pages26
JournalPsychometrika
Volume50
Issue number3
DOIs
StatePublished - Sep 1 1985

Fingerprint

Alternating Least Squares
Weighted Least Squares
Unfolding
Least-Squares Analysis
Three-way Data
Metric
Objective function
Fractional Factorial
Design of experiments
Research Design
Experimental design
Rendering
Proximity
Flexibility
Model
Robustness
Methodology

All Science Journal Classification (ASJC) codes

  • Psychology(all)
  • Applied Mathematics

Cite this

Desarbo, Wayne ; Douglas Carroll, J. / Three-way metric unfolding via alternating weighted least squares. In: Psychometrika. 1985 ; Vol. 50, No. 3. pp. 275-300.
@article{895aba5ef6d046e48d74e317c282caa7,
title = "Three-way metric unfolding via alternating weighted least squares",
abstract = "Three-way unfolding was developed by DeSarbo (1978) and reported in DeSarbo and Carroll (1980, 1981) as a new model to accommodate the analysis of two-mode three-way data (e.g., nonsymmetric proximities for stimulus objects collected over time) and three-mode, three-way data (e.g., subjects rendering preference judgments for various stimuli in different usage occasions or situations). This paper presents a revised objective function and new algorithm which attempt to prevent the common type of degenerate solutions encountered in typical unfolding analysis. We begin with an introduction of the problem and a review of three-way unfolding. The three-way unfolding model, weighted objective function, and new algorithm are presented. Monte Carlo work via a fractional factorial experimental design is described investigating the effect of several data and model factors on overall algorithm performance. Finally, three applications of the methodology are reported illustrating the flexibility and robustness of the procedure.",
author = "Wayne Desarbo and {Douglas Carroll}, J.",
year = "1985",
month = "9",
day = "1",
doi = "10.1007/BF02294106",
language = "English (US)",
volume = "50",
pages = "275--300",
journal = "Psychometrika",
issn = "0033-3123",
publisher = "Springer New York",
number = "3",

}

Three-way metric unfolding via alternating weighted least squares. / Desarbo, Wayne; Douglas Carroll, J.

In: Psychometrika, Vol. 50, No. 3, 01.09.1985, p. 275-300.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Three-way metric unfolding via alternating weighted least squares

AU - Desarbo, Wayne

AU - Douglas Carroll, J.

PY - 1985/9/1

Y1 - 1985/9/1

N2 - Three-way unfolding was developed by DeSarbo (1978) and reported in DeSarbo and Carroll (1980, 1981) as a new model to accommodate the analysis of two-mode three-way data (e.g., nonsymmetric proximities for stimulus objects collected over time) and three-mode, three-way data (e.g., subjects rendering preference judgments for various stimuli in different usage occasions or situations). This paper presents a revised objective function and new algorithm which attempt to prevent the common type of degenerate solutions encountered in typical unfolding analysis. We begin with an introduction of the problem and a review of three-way unfolding. The three-way unfolding model, weighted objective function, and new algorithm are presented. Monte Carlo work via a fractional factorial experimental design is described investigating the effect of several data and model factors on overall algorithm performance. Finally, three applications of the methodology are reported illustrating the flexibility and robustness of the procedure.

AB - Three-way unfolding was developed by DeSarbo (1978) and reported in DeSarbo and Carroll (1980, 1981) as a new model to accommodate the analysis of two-mode three-way data (e.g., nonsymmetric proximities for stimulus objects collected over time) and three-mode, three-way data (e.g., subjects rendering preference judgments for various stimuli in different usage occasions or situations). This paper presents a revised objective function and new algorithm which attempt to prevent the common type of degenerate solutions encountered in typical unfolding analysis. We begin with an introduction of the problem and a review of three-way unfolding. The three-way unfolding model, weighted objective function, and new algorithm are presented. Monte Carlo work via a fractional factorial experimental design is described investigating the effect of several data and model factors on overall algorithm performance. Finally, three applications of the methodology are reported illustrating the flexibility and robustness of the procedure.

UR - http://www.scopus.com/inward/record.url?scp=0010098637&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0010098637&partnerID=8YFLogxK

U2 - 10.1007/BF02294106

DO - 10.1007/BF02294106

M3 - Article

AN - SCOPUS:0010098637

VL - 50

SP - 275

EP - 300

JO - Psychometrika

JF - Psychometrika

SN - 0033-3123

IS - 3

ER -