• No results found

Advances in multidimensional unfolding Busing, F.M.T.A.

N/A
N/A
Protected

Academic year: 2021

Share "Advances in multidimensional unfolding Busing, F.M.T.A."

Copied!
15
0
0

Bezig met laden.... (Bekijk nu de volledige tekst)

Hele tekst

(1)

Advances in multidimensional unfolding

Busing, F.M.T.A.

Citation

Busing, F. M. T. A. (2010, April 21). Advances in multidimensional

unfolding. Retrieved from https://hdl.handle.net/1887/15279

Version: Not Applicable (or Unknown)

License: Licence agreement concerning inclusion of doctoral thesis in the Institutional Repository of the University of Leiden

Downloaded from: https://hdl.handle.net/1887/15279

Note: To cite this publication please use the final published version (if

applicable).

(2)

advances in

multidimensional

unfolding

(3)
(4)

advances in multidimensional unfolding

Proefschrift

ter verkrijging van de graad van Doctor aan de Universiteit Leiden, op gezag van Rector Magnificus prof. mr. P.F. van der Heijden, volgens besluit van het College voor Promoties te verdedigen op woensdag 21 april 2010 klokke 15:00 uur door Franciscus Martinus Theodorus Antonius Busing geboren te Amsterdam in 1963

(5)

promotiecommissie

Promotor: prof. dr. W. J. Heiser

Overige leden: prof. dr. I. van Mechelen(Katholieke Universiteit Leuven)

prof. dr. P. J. F. Groenen (Erasmus Universiteit Rotterdam)

prof. dr. J. J. Meulman (Universiteit Leiden)

dr. M. de Rooij (Universiteit Leiden)

(6)
(7)

Busing, Franciscus Martinus Theodorus Antonius Advances in Multidimensional Unfolding

Subject headings: unfolding / penalty / restrictions / least squares Copyright © 2010 by Frank Busing

Cover design by Josefien Croese

Printed by Gildeprint Drukkerijen, Enschede, the Netherlands

All rights reserved. This work may not be copied, reproduced, or translated in whole or in part without written permission of the publisher(s), except for brief excerpts in connection with reviews or scholarly analysis. Use with any form of information storage and retrieval, electronic adaptation or whatever, computer software, or by similar or dissimilar methods now known or developed in the future is also strictly forbidden without written permission of the publisher.

Some parts of this work are reproduced by permission; those copyright-holders are: The British Psychological Society, Springer Science+Business Media, and Reed Elsevier.

isbn 978-94-610-8025-7

(8)

weet je wat nu zo zonde is dat ik dit op schrijf zonder jou

— Bert Schierbeek

Dedicated to the loving memory of Ton Busing 1931 – 1990

(9)
(10)

publications

Some ideas have appeared previously in the following publications from the same author:

Busing, F.M.T.A., Commandeur, J.J.F., & Heiser, W.J. (1997). PROXSCAL:

A multidimensional scaling program for individual differences scaling with constraints. In W. Bandilla & F. Faulbaum (Eds.), Softstat ’97, advances in statistical software (pp. 237–258). Stuttgart, Germany: Lucius.

Heiser, W.J., & Busing, F.M.T.A. (2004). Multidimensional scaling and unfold- ing of symmetric and asymmetric proximity relations. In D. Kaplan (Ed.), The Sage handbook of quantitative methodology for the social sciences (pp. 25–48).

Thousand Oaks, CA: Sage Publications, Inc.

Busing, F.M.T.A., & Van Deun, K. (2005). Unfolding Degeneracies’ History.

In K. Van Deun, Degeneracies in multidimensional unfolding (pp. 29–75). Un- published doctoral dissertation, Catholic University Leuven.

Van Deun, K., Groenen, P.J.F., Heiser, W.J., Busing, F.M.T.A., & Delbeke, L.

(2005). Interpreting degenerate solutions in unfolding by use of the vector model and the compensatory distance model. Psychometrika, 70(1), 23–47.

Busing, F.M.T.A., Groenen, P.J.F., & Heiser, W.J. (2005). Avoiding degeneracy in multidimensional unfolding by penalizing on the coefficient of variation.

Psychometrika, 70(1), 71–98.

Busing, F.M.T.A. (2006). Avoiding degeneracy in metric unfolding by penaliz- ing the intercept. British Journal of Mathematical and Statistical Psychology, 59, 419–427.

Busing, F.M.T.A., & de Rooij, M. (2009). Unfolding incomplete data: Guide- lines for unfolding row-conditional rank order data with random missings.

Journal of Classification, 26, 329–360.

Busing, F.M.T.A., Heiser, W.J., & Cleaver, G. (2010). Restricted unfolding:

Preference analysis with optimal transformations of preferences and attributes.

Food Quality and Preference, 21(1), 82–92.

(11)
(12)

contents

1 Introduction 

2 Unfolding degeneracies’ history 

. Introduction 

. Foundations of multidimensional unfolding 

. Roskam, 1968 

. Kruskal and Carroll, 1969 

. Lingoes, 1977 

. Heiser, 1981 

. Borg and Bergermaier, 1982 

. De Leeuw, 1983 

. DeSarbo and Rao, 1984

. Heiser, 1989 

. Kim, Rangaswamy, and DeSarbo, 1999 

. Summary 

. Recent developments 

3 The intercept penalty 

. Introduction 

. Example 

. Metric unfolding 

. Degeneracy 

. Penalizing the intercept 

. Example (continued) 

. Conclusion 

.A Penalized interval transformation 

.B Example: ibm spss prefscal specification for pmse 

.C Example: matlab code for pmse 

4The coefficient of variation penalty 

. Introduction 

. Badness-of-fit functions 

. Penalizing the coefficient of variation 

. Simulation study 

. Applications 

. Summary 

(13)

5 Restricted Unfolding 

. Introduction 

. The restricted unfolding model 

. Case study 

. Optimizing product development 

. Comparison 

. Discussion 

6 Unfolding incomplete data 

. Introduction 

. Unfolding 

. Missing data 

. Monte Carlo simulation study 

. Example 

. Conclusion 

.A Simulation study 

7 Conclusion 

. The intercept penalty 

. The coefficient of variation penalty 

. Restricted unfolding 

. Unfolding incomplete data 

. Final conclusions 

Technical appendix A Notation overview 141

A. Notation conventions 

A. Symbols 

A. Functions 

A. Acronyms 

B Least squares unfolding algorithm 147 C Pre-Processing 151

C. Preliminary work 

C. Initial configuration 

D Transformation update 161 D. Majorization functions 

D. Transformation functions 

(14)

E Configuration update 175 E. Common space update 

E. Two-way unfolding models 

E. Three-way unfolding models 

E. Coordinate restrictions 

E. Variable restrictions 

E. Other restrictions 

F Post-Processing 193

F. Algorithm termination 

F. Uniqueness 

F. Multiple analyses 

F. Additional analyses 

G Results 207

G. Table output 

G. Figure output 

G. Fit measures 

G. Variation measures 

G. Degeneracy indices 

Glossary of Solutions 

References 

Author index 

Subject index 

Summary (in Dutch) 

Curriculum vitae 

Colophon 

(15)

Referenties

GERELATEERDE DOCUMENTEN

genfold- 2 (DeSarbo & Rao, 1984) (Kim, Rangaswamy, & DeSarbo, 1999, even mention a genfold) was never made publicly available, but the loss function is simple enough to

In this chapter, a simple but effective solution is proposed to the degener- acy problem in metric unfolding: Penalize the undesirable intercept to avoid identical

To avoid such degeneracies, Kruskal and Carroll (1969) proposed alterna- tive badness-of-fit functions that incorporate normalization factors based on the variance of the

This rules in favor of internal preference analysis (over external preference analysis) and we will therefor compare the restricted unfolding solution with three such analyses, a

Figure 6.7 Boxplots of the recovery measures ( φ xy , φ y , and τ b , for the left-hand, middle, and right-hand panels, respectively; lower left-hand panel includes both φ high

Examples of such devel- opments were presented in subsequent chapters: Chapter 5 elaborated on a previously published model extension, restricting the coordinates to be

Depending on the individual differences model and the restrictions on the configuration, updates are determined for the row coordinates X, the column coordinates Y, the space weights

Absolutely or completely degenerate solution — A flawless but purposeless zero stress solution without variation in the transformed preferences or the distances that cannot be