A general, flexible LAtent DIscriminant model is described. LADI is a model-based clustering procedure, derived from a specific conceptualization in which the discrimination problem is viewed in a latent mixture context. The basic model yields maximum likelihood (ML) estimates of mixing parameters and structural parameters that define the latent clusters in terms of the responses to a set of descriptor variables. Among other features, the model accommodates descriptor variables having different scale properties, allows for the investigation of group structure, provides a statistical test of the number of latent clusters to retain, and allows for constraints to be imposed on the solution.
Get full access to this article
View all access options for this article.
References
1.
AitkinM. (1980), “Mixture Applications of the EM Algorithm in GLIM,” in COMPSTAT (Proceedings in Computational Statistics). Vienna: Physica Verlag, 537–41.
2.
AitkinM., AndersonD., and HindeJ. (1981), “Statistical Modeling of Data on Teaching Styles,” Journal of the Royal Statistical Society, A144, 419–61.
3.
AkaikeH. (1974), “A New Look at the Statistical Model Identification,” IEEE Transactions on Automatic Control, 19, 716–23.
4.
ArnoldStephen John (1979), “A Test for Clusters,” Journal of Marketing Research, 16 (November), 545–51.
5.
BasfordKay E. and GeoffreyL. McLachlan (1985), “Cluster Analysis in a Randomized Complete Block Design,” Communication in Statistics—Theory and Methods, 14, 451–63.
6.
BurtC. C. (1941), The Factors of the Mind: An Introduction to Factor Analysis in Psychology. New York: Macmillan Publishing Co.
7.
CloggClifford C. (1977), “Unrestricted and Restricted Maximum Likelihood Latent Structure Analysis: A Manual for Users,” Working Paper No. 1977-09, Pennsylvania State University.
8.
DayNeil E. (1969), “Estimating the Components of a Mixture of Normal Distributions,” Biometrika, 56, 463–74.
9.
DempsterA. P., LairdN. M., and RubinD. B. (1977), “Maximum Likelihood from Incomplete Data Via the EM Algorithm,” Journal of the Royal Statistical Society, B39, 1–38.
10.
DillonWilliam R. (1978), “The Performance of the Linear Disciminant Function in Nonoptimal Situations and the Estimation of Classification Error Rates: A Review of Recent Findings,” Journal of Marketing Research, 15 (August), 370–81.
11.
DillonWilliam R. (1979), “Analyzing Large Multiway Contingency Tables: A Simple Method for Selecting Variables,” Journal of Marketing, 43 (Fall), 92–102.
12.
DillonWilliam R., ThomasJ. Madden, and NarendraMulani (1983), “Scaling Models for Categorical Variables: An Application of Latent Structure Models,” Journal of Consumer Research, 10 (September), 209.
13.
FrankRonald, WilliamMassy, and YoramWind (1972), Market Segmentation. Englewood Cliffs, NJ: Prentice-Hall, Inc.
14.
GoodmanLeo A. (1974a), “The Analysis of Systems of Qualitative Variables When Some of the Variables are Unobservable. Part I: A Modified Latent Structure Approach,” American Journal of Sociology, 79 (5), 1179–1259.
GreenPaul E., FrankJ. Carmone, and WachspressDavid P. (1976). “Consumer Segmentation Via Latent Class Analysis,” Journal of Consumer Research, 3 (3), 170–4.
17.
GroverRajiv and WilliamR. Dillon (1985), “A Probabilistic Model for Testing Hypothesized Hierarchical Market Structures,” Marketing Science, 4 (Fall), 312–35.
18.
GroverRajiv and WilliamR. Dillon and SrinivasanV. (1987). “A Simultaneous Approach to Market Segmentation and Market Structuring,” Journal of Marketing Research, 24 (May), 139–53.
19.
HopeA. C. (1968), “A Simplified Monte Carlo Significance Test Procedure,” Journal of the Royal Statistical Society, B30, 582–98.
20.
JöreskogKarl G. and DagSörbom (1979), Advances in Factor Analysis and Structural Equation Models. Cambridge, MA: Abt Books.
21.
JöreskogKarl G. and DagSörbom (1984), LISREL V Analysis of Linear Structural Relationships by the Method of Maximum Likelihood. Mooresville, IN: Scientific Software.
22.
KruskalWilliam H. and TanurJ. M. (1978), International Encyclopedia of Statistics. New York: The Free Press.
23.
KumarAjith and WilliamR. Dillon (1987), “Constrained Discrimination via MDI Estimation: The Use of Additional Information in Segmentation Analysis,” Journal of Marketing Research, 24 (November), 396–403.
24.
LazarsfeldPaul F. and NeilW. Henry (1968), Latent Structure Analysis. New York: Houghton-Mifflin Company.
25.
MaddenThomas J. and WilliamR. Dillon (1982), “Causal Analysis and Latent Class Models: An Application to a Communication Hierarchy of Effects Model,” Journal of Marketing Research, 19 (November), 472–90.
26.
MalhotraNaresh K. (1987), “Analyzing Marketing Research Data with Incomplete Information on the Dependent Variable,” Journal of Marketing Research, 24 (February), 74–84.
27.
MantonKenneth G., EricStallard, MaxWoodbury, TolleyH. Dennis, and AnatoliI. Yashin (1987), “Grade-of-Membership Techniques for Studying Complex Event History Processes with Unobserved Covariates,” in Sociological Methodology 1987, CloggC. C., ed. Washington, DC: American Sociology Association, 309–46.
28.
McDonaldRonald P. (1985), Factor Analysis and Related Methods. Hillsdale, NJ: Lawrence Erlbaum Associates, Publishers.
29.
McHughR. B. (1956), “Efficient Estimation and Local Identification in Latent Class Analysis,” Psychometrika, 21 (4), 331–47.
30.
McLachlanGeoffrey L. and KayE. Basford (1988), Mixture Models: Inference and Applications to Clustering. New York: Marcel Dekker, Inc.
31.
MilliganG. W. (1981), “A Monte Carlo Study of Thirty Internal Criterion Clustering Algorithms,” Psychometrika, 46 (2), 187–99.
32.
SundbergR. (1974), “Maximum Likelihood Theory for Incomplete Data From an Exponential Family,” Scandinavian Journal of Statistics, 1 (2), 1–49.
33.
TitteringtonD. M., SmithA. F. M., and MarkovU. E. (1985), Statistical Analysis of Finite Mixture Distributions. New York: John Wiley & Sons, Inc.
34.
WindYoram (1978), “Issues and Advances in Segmentation Research,” Journal of Marketing Research, 15 (August), 317–37.
35.
WolfeJ. H. (1970), “Pattern Clustering by Multivariate Mixture Analysis,” Multivariate Behavioral Research, 5 (3), 329–50.
