Probabilistic multidimensional scaling (MDS) models, in comparison with the deterministic ones, offer several theoretical advantages that are likely to appeal to marketing researchers. These advantages are based on asymptotic sampling theory assuming that an explicated error distribution holds true. Whether such models are perceived as practical and useful by marketing researchers, however, will depend partially on the robustness and small-sample properties of their estimators. The error underlying the judgments may very well violate the distributional assumptions, and the typical sample size in marketing applications is not likely to meet the asymptotic requirements. The authors examine the robustness and small-sample properties of PROSCAL, a probabilistic MDS algorithm based on a multivariate generalization of Thurstone's pair comparison model. The results of two extensive simulations experimentally manipulating number of subjects, number of stimuli, and type of error distribution and its variance suggest that PROSCAL estimators are robust to violations of the assumption of normality of the error term within the manipulated ranges of the parameter values. Also, goodness of recovery and dimensionality tests are fairly accurate for sample sizes as small as nine.
Get full access to this article
View all access options for this article.
References
1.
AcitoFrank and RonaldD. Anderson (1986), “A Simulation Study of Factor Score Indeterminacy,” Journal of Marketing Research, 23 (May), 111–18.
2.
AkaikeHirotugu (1973), “Information Theory and an Extension of the Maximum Likelihood Principle,” in Second International Symposium on Information Theory, PetrovB.N. and CsakiB. F., eds. Budapest: Academiai Kiado, 267–81.
3.
AkaikeHirotugu (1974), “A New Look at the Statistical Model Identification,” IEEE Transactions on Automatic Control, AC-19, 716–23.
4.
AkaikeHirotugu (1981), “Likelihood of a Model and Information Criteria,” Journal of Econometrics, 16 (May), 3–14.
5.
AkaikeHirotugu (1987), “Factor Analysis and AIC,” Psychometrika, 52 (September), 317–32.
6.
BabakusEmin, FergusonCarl E.Jr., and KarlG. Jöreskog (1987), “The Sensitivity of Confirmatory Maximum Likelihood Factor Analysis to Violations of Measurement Scale and Distributional Assumptions,” Journal Marketing Research, 24 (May), 222–8.
7.
BorgIngwer and DetlevLeutner (1985), “Measuring the Similarity of MDS Configurations,” Multivariate Behavioral Research, 20 (July), 325–34.
8.
BozdoganHamparsum (1987), “Model Selection and Akaike's Information Criterion (AIC): The General Theory and Its Analytical Extensions,” Psychometrika, 52 (September), 345–70.
9.
CarrollJ. Douglas and ArabiePhipps (1980), “Multidimensional Scaling,” Annual Review of Psychology, 31, 607–49.
10.
DayGeorge S., AllanD. Shocker, and RajendraSrivastava (1979), “Customer Oriented Approaches to Identifying Product Markets,” Journal of Marketing, 43 (Fall), 8–19.
11.
DrögeCornelia and ReneY. Darmon (1987), “Associative Positioning Strategies Through Comparative Advertising: Attribute Versus Overall Similarity Approaches,” Journal of Marketing Research, 24 (November), 377–88.
12.
FeldtLeonard S. and MoharramW. Mahmoud (1958), “Power Function Charts for Specification of Sample Size in Analysis of Variance,” Psychometrika, 23 (September), 201–10.
13.
FishmanGeorge S. (1973), Concepts and Methods in Discrete Event Digital Simulation, New York: John Wiley & Sons, Inc.
14.
GreenPaul E. (1975), “Marketing Applications of MDS: Assessment and Outlook,” Journal of Marketing, 39 (January), 24–31.
15.
HefnerR. (1958), “Extensions of the Law of Comparative Judgment to Discriminable and Multidimensional Stimuli,” PhD dissertation, Psychology Department, University of Michigan.
16.
KlahrDavid (1969), “A Monté Carlo Investigation of the Statistical Significance of Kruskal's Nonmetric Scaling Procedure,” Psychometrika, 34 (September), 319–30.
17.
KruskalJ. B. (1964a), “Multidimensional Scaling by Optimizing Goodness of Fit to a Nonmetric Hypothesis,” Psychometrika, 29 (March), 1–27.
18.
KruskalJ. B. (1964b), “Nonmetric Multidimensional Scaling: A Numerical Method,” Psychometrika, 29 (June), 28–42.
19.
KruskalJ. B., YoungForrest W., and JudithB. Seery (1973), “How to Use KYST, A Very Flexible Program to Do Multidimensional Scaling and Unfolding.” Murray Hill, NJ: Bell Telephone Laboratories (mimeographed).
20.
LindmanHarold R. (1974), Analysis of Variance in Complex Experimental Designs. San Francisco: W. H. Freeman and Company.
21.
MacKayDavid B. (1983), “Alternative Probabilistic Scaling Models for Spatial Data,” Geographical Analysis, 15 (July) 173–86.
22.
MacKayDavid B. (1988), “Probabilistic Multidimensional Scaling: An Anisotropic Model for Distance Judgments,” Journal of Mathematical Psychology.
23.
MacKayDavid B. and JosephL. Zinnes (1981), “Probabilistic Scaling of Spatial Distance Judgments,” Geographical Analysis, 13 (January), 21–37.
24.
MacKayDavid B. and JosephL. Zinnes (1984), “PROSCAL: A Program for Probabilistic Scaling,” Discussion Paper 218, Graduate School of Business, Indiana University.
25.
MacKayDavid B. and JosephL. Zinnes (1986), “A Probabilistic Model for the Multidimensional Scaling of Proximity and Preference Data,” Marketing Science, 5 (Fall), 325–44.
26.
McIntyreShelby H., DavidMontgomery, SrinivasanV., and BartonWeitz (1983), “Evaluating the Statistical Significance of Models Developed by Stepwise Regression,” Journal of Marketing Research, 20 (February), 1–11.
27.
RamsayJames O. (1977), “Maximum Likelihood Estimation in Multidimensional Scaling,” Psychometrika, 42 (June), 241–66.
28.
RamsayJames O. (1978a), “Confidence Regions for Multidimensional Scaling Analysis,” Psychometrika, 43 (June), 145–60.
29.
RamsayJames O. (1978b) Multiscale: Four Programs for Multidimensional Scaling by the Method of Maximum Likelihood. Chicago: National Educational Resources.
30.
RamsayJames O. (1980), “The Joint Analysis of Direct Ratings, Pairwise Preferences and Dissimilarities,” Psychometrika, 45 (June), 149–65.
31.
SchonemannPeter H. and WangMing Mei (1972), “An Individual Difference Model for the Multidimensional Analysis of Preference Data,” Psychometrika, 37 (September), 275–308.
32.
SpenceIan (1979), “A Simple Approximation for Random Rankings STRESS Values,” Multivariate Behavioral Research, 14 (July), 355–65.
33.
SpenceIan and JohnC. Ogilvie (1973), “A Table of Expected Stress Values for Random Rankings in Nonmetric Multidimensional Scaling,” Multivariate Behavioral Research, 8 (October), 511–17.
34.
TakaneYoshio (1978a), “A Maximum Likelihood Method for Nonmetric Multidimensional Scaling: I. The Case in Which All Empirical Pairwise Orderings Are Independent—Theory,” Japanese Psychological Reviews, 20, 7–17.
35.
TakaneYoshio (1978b), “A Maximum Likelihood Method for Nonmetric Multidimensional Scaling: I. The Case in Which All Empirical Pairwise Orderings Are Independent—Evaluations,” Japanese Psychological Reviews, 20, 105–14.
36.
TakaneYoshio (1980), “Maximum Likelihood Estimation in the Generalized Case of Thurstone's Model of Comparative Judgment,” Japanese Psychological Reviews, 22, 188–96.
37.
TakaneYoshio (1981), “Multidimensional Successive Categories Scaling: A Maximum Likelihood Method,” Psychometrika, 46 (March), 9–28.
ThurstoneL. L. (1927), “Psychophysical Analysis,” American Journal of Psychology, 38 (July), 368–89.
40.
TverskyAmos, YosefRinott, and CharlesM. Newman (1983), “Nearest Neighbor Analysis of Point Processes: Applications to Multidimensional Scaling,” Journal of Mathematical Psychology, 27 (September), 235–50.
41.
UrbanGlen L. and JohnR. Hauser (1980), Design and Marketing of New Products. Englewood Cliffs, NJ: Prentice-Hall, Inc.
YoungForrest W. (1970), “Nonmetric Multidimensional Scaling: Recovery of Metric Information,” Psychometrika, 35 (December), 455–73.
44.
YoungForrest W. (1984), “Scaling,” Annual Review of Psychology, 35, 55–81.
45.
YoungForrest W. and RostyslawLewyckyj (1979), ALSCAL-4 User's Guide. Chapel Hill, NC: University of North Carolina (mimeographed).
46.
ZinnesJoseph L. and DavidMacKay (1983), “Probabilistic Multidimensional Scaling: Complete and Incomplete Data,” Psychometrika, 48 (March), 27–48.
47.
ZinnesJoseph L. and DavidMacKay (1987), “Probabilistic Multidimensional Analysis of Preference Ratio Judgments,” Communication and Cognition, 20 (1), 17–44.
