Managers are unlikely to keep current with advanced developments in market-response analysis, and technical analysts often lack the marketplace knowledge of the many product categories they must track through syndicated data; this is a recipe for bad decisions. The authors present methods based on three-mode factor analysis and multivariate regression that can help both analysts and managers make better decisions regarding whether UPCs should be aggregated into brand units and, if so, how should the aggregation be done; which marketing instruments to track; and how to disentangle correlated promotional strategies. The practicality of this approach is demonstrated by an application to UPC-level data (25 UPCs, seven marketing instruments, and 156 weeks). In this example, to aggregate UPCs within a manufacturer into brand units would distort the relations between the marketing instruments and market responses. A multivariate regression from the competitive-component scores provides a methodologically sound and practical method for calibrating market response in such cases.
Get full access to this article
View all access options for this article.
References
1.
BellDavid E., KeeneyRalph L., and LittleJohn D. C. (1975), “A Market Share Theorem,”Journal of Marketing Research, 7(May), 136–41.
2.
CarpenterGregory A., CooperLee G., HanssensDominique M., and MidgleyDavid F. (1988), “Modeling Asymmetric Competition,”Marketing Science, 7(4), 393–412.
3.
CarrollJ. Douglas, and ArabiePhipps (1980), “Multidimensional Scaling,” in Annual Review of Psychology, Vol. 31, RosensweigM. R., and PorterL. W., eds. Palo Alto, CA: Annual Reviews, 607–49.
4.
CarrollJ., ArabieDouglas Phipps, and ChangJih-Jie (1970), “Analysis of Individual Differences in Multidimensional Scaling Via an N-Way Generalization of ‘Eckart-Young’ Decomposition,”Psychometrika, 35(September), 283–320.
5.
CarrollJ. Douglas, PruzanskySandra, and KruskalJoseph B. (1980), “CANDELINC: A General Approach to Multidimensional Analysis of Many-Way Arrays with Linear Constraints on Parameters,”Psychometrika, 45(1), 3–24.
6.
CooperLee G. (1988), “Competitive Maps: The Structure Underlying Asymmetric Cross Elasticities,”Management Science, 34(6), 299–319.
7.
CooperLee G. (1993), “Market-Share Models,” in Handbooks in Operations Research and Management Science: Marketing, EliashbergJ., and LilienG. L., eds. Amsterdam: North-Holland, 259–314.
8.
CooperLee G., deLeeuwJan, and SogomonianArum G. (1991), “An Imputation Method for Dealing With Missing Data in Regression,”Applied Stochastic Models and Data Analysis, 7(3), 213–35.
9.
CooperLee G., and NakanishiMasao (1988), Market-Share Analysis.Boston: Kluwer Academic Publishers.
10.
EstesWilliam K. (1956), “The Problem of Inference from Curves Based on Group Data,”Psychological Bulletin, 53(2), 134–40.
11.
FaderPeter S., HardieBruce G. S., and WalshJohn W. (1994), “Modeling Consumer Choice Among SKUs,” Wharton Marketing Department Working Paper #94-007, February.
12.
FoekensE. W., LeeflangP. S. H., and WittinkD. R. (1992), “Asymmetric Market Share Modeling with Many Competitive Items Using Market Level Scanner Data,” working paper, University of Groningen.
13.
HarshmanR. A. (1970), “Foundations of the PARAFAC Procedure: Models and Conditions for an ‘Explanatory’ Multi-Mode Factor Analysis,”UCLA Working Papers in Phonetics, 16, 1–84.
14.
KiersH. A. L. (1991), “Hierarchical Relations Among Three-Way Methods,”Psychometrika, 56(September), 449–70.
15.
KroonenbergP. M. (1983), Three-Mode Principal Component Analysis.Leiden, The Netherlands: DSWO Press.
16.
KroonenbergP. M. (1992), “Three-Mode Component Models: A Survey of the Literature,”Statistica Applicata, 4, 619–33.
17.
KroonenbergP. M., and de LeeuwJ. (1977), “TUCKALS2: A Principal Component Analysis of Three-Mode Data,” Research Bulletin RB. 001-77, Department of Data Theory, University of Leiden, Leiden, The Netherlands.
18.
KroonenbergP. M., and de LeeuwJ. (1980), “Principal Component Analysis of Three-Mode Data by Means of Alternating Least Squares Algorithms,”Psychometrika, 45(March), 69–97.
19.
LawH. G., SnyderC. W.Jr., HattieJ. A., and McDonaldR. P. (1984), Research Methods for Multimode Data Analysis.New York: Praeger Press.
20.
LittleR. J. A., and RubinD. B. (1987), Statistical Analysis with Missing Data.New York: John Wiley & Sons.
21.
LittleR. J. A., and SchluchterM. D. (1985), “Maximum Likelihood Estimation for Mixed Continuous and Categorical Data with Missing Values,”Biometrika, 72(3), 497–512.
22.
MalhotraNaresh K. (1987), “Analyzing Marketing Research Data With Incomplete Information on the Dependent Variable,”Journal of Marketing Research, 24(February), 74–84.
23.
MulaikS. (1972), The Foundations of Factor Analysis.New York: McGraw-Hill.
24.
OlkinI., and TateR. F. (1961), “Multivariate Correlation Models with Mixed Discrete and Continuous Variables,”Annals of Mathematical Statistics, 32(June), 448–65.
25.
RamsayJ. O., ten BergeJ., and StyanG. P. H. (1984), “Matrix Correlation,”Psychometrika, 49, 403–23.
26.
TorgersonW. S. (1958), Theory and Methods of Scaling.New York: John Wiley & Sons.
27.
TuckerLedyard R (1957), “Transformation of Predictor Variables to a Simplified Regression Structure,”Technical Report.Princeton, NJ: Educational Testing Service.
28.
TuckerLedyard R (1966), “Some Mathematical Notes on Three-Mode Factor Analysis,”Psychometrika, 31(September), 279–311.
29.
TuckerLedyard R (1972), “Relations Between Multidimensional Scaling and Three-Mode Factor Analysis,”Psychometrika, 37, 3–27.
30.
TuckerLedyard R, CooperLee G., and MeredithWilliam (1972), “Obtaining Squared Multiple Correlations from a Correlation Matrix Which May Be Singular,”Psychometrika, 37(2), 143–48.
31.
TuckerLedyard R, and MessickSamuel (1963), “An Individual Differences Model for Multidimensional Scaling,”Psychometrika, 28(December), 333–67.
32.
Vanden AbeeleP., GijsbrechtE., and VanhueleM. (1990), “Specification and Empirical Evaluation of a Cluster-Asymmetry Market Share Model,”International Journal of Research in Marketing, 7(4), 223–47.
