Cluster analysis via a finite mixture model approach is considered. With this approach to clustering, the data can be partitioned into a specified number of clusters g by first fitting a mixture model with g components. An outright clustering of the data is then obtained by assigning an observation to the component to which it has the highest estimated posterior probability of belonging; that is, the ith cluster consists of those observations assigned to the ith component (i = 1,..., g). The focus is on the use of mixtures of normal components for the cluster analysis of data that can be regarded as being continuous. But attention is also given to the case of mixed data, where the observations consist of both continuous and discrete variables.
McLachlan GJ , Basford, KE.Mixture models: inference and applications to clustering. New York: Marcel Dekker , 1988.
3.
Dempster AP , Laird NM , Rubin DB.Maximum likelihood from incomplete data via the EM algorithm (with discussion) . Journal of the Royal Statistical Society B1977; 39: 1-38 .
4.
McLachlan GJ , Krishnan T.The EM algorithm and extensions. New York: Wiley , 1997.
5.
Hawkins DM , Muller MW , ten Krooden JA.Cluster analysis. In Hawkins DM , ed. Topics in applied multivariate analysis. Cambridge: Cambridge University Press , 1982; 303-356.
6.
Aitkin M , Anderson D , Hinde J.Statistical modelling of data on teaching styles (with discussion) . Journal of the Royal Statistical Society B1981; 144: 419-461 .
Ng, SK , McLachlan, GJ.On the choice of the number of blocks with the incremental EM algorithm for the fitting of normal mixtures . Statistics and Computing2003; 13: 45-55 .
9.
Coleman D , Dong X , Hardin J , Rocke DM , Woodruff DL.Some computational issues in cluster analysis with no a priori metric . Computational Statistics and Data Analysis1999; 31: 1-11 .
10.
Biernacki C , Celeux G , Govaert G.Choosing starting values for the EM algorithm for getting the highest likelihood in multivariate Gaussian mixture models . Computational Statistics and Data Analysis2003; 41: 561-575 .
11.
McLachlan GJ , Peel D , Basford KE , Adams P.The EMMIX software for the fitting of mixtures of normal and t-components . Journal of Statistical Software1999; 4 (No. 2).
12.
Fraley C , Raftery AE.How many clusters? Which clustering method? Answers via model-based cluster analysis . Computer Journal1998; 41: 578-588 .
13.
Hartley HO , Rao JNK.Classification and estimation in analysis of variance problems . International Statistical Review1968; 36: 141-147 .
14.
John S.On identifying the population of origin of each observation in a mixture of observations from two normal populations . Technometrics1970; 12: 553-563 .
15.
Scott AJ , Symons MJ.Clustering methods based on likelihood ratio criteria . Biometrics1971; 27: 387-397 .
16.
McLachlan GJ.The classification and mixture maximum likelihood approaches to cluster analysis. In Krishnaiah PR , Kanal L , eds. Handbook of statistics, Volume 2. Amsterdam: North-Holland , 1982; 199-208.
17.
Bryant PG.Large-sample results for optimization-based clustering . Journal of Classification1991; 8: 31-44 .
Friedman HP , Rubin H.On some invariant criteria for grouping data . Journal of the American Statistical Association1967; 62: 1159-1178 .
20.
McLachlan GJ.On bootstrapping the likelihood ratio test statistic for the number of components in a normal mixture . Applied Statistics1987; 36: 318-324 .
21.
Schwarz G.Estimating the dimension of a model . Annals of Statistics1978; 6: 461-464 .
22.
Biernacki C , Celeux G , Govaert G.Assessing a mixture model for clustering with the integrated completed likelihood . IEEE Transactions on Pattern Analysis and Machine Intelligence2000; 22: 719-725 .
23.
McLachlan GJ , Peel D.Robust cluster analysis via mixtures of multivariate t-distributions. In Amin A , Dori D , Pudil P , Freeman H , eds. Lecture notes in computer science, Volume 1451. Berlin: Springer-Verlag , 1998; 658-666.
24.
Peel D. and McLachlan. GJ.Robust mixture modelling using the t-distribution . Statistics and Computing2000; 10: 335-344 .
25.
Hennig C.Breakdown points of maximum likelihood-estimators of location-scale mixtures . Annals of Statistics2002; in press.
Bensmail H , Celeux G , Raftery AE , Robert CP.Inference in model-based cluster analysis . Statistics and Computing1997; 7: 1-10 .
28.
McLachlan GJ , Peel, D.Mixtures of factor analyzers , In Langley P , ed. Proceedings of the Seventeenth International Conference on Machine Learning. San Francisco: Morgan Kaufmann, 2000; 599-606 .
29.
McLachlan GJ , Peel D , Bean RW.Modelling high-dimensional data by mixtures of factor analyzers . Computational Statistics and Data Analysis2003; 41: 379-388 .
30.
Ghahramani Z , Hinton GE.The EM algorithm for factor analyzers. Technical Report No. CRG-TR-96-1, Toronto: The University of Toronto , 1997.
31.
Tipping ME , Bishop CM.Mixtures of probabilistic principal component analysers . Neural Computation1999; 11: 443-482 .
32.
Meng XL , van Dyk D.The EM algorithm - an old folk song sung to a fast new tune (with discussion) . Journal of the Royal Statistical Society B1997; 59: 511-567 .
33.
Titterington DM , Murray GD , Murray LS , Spiegelhalter DJ , Skene AM , Habbema JDF , Gelpke, GJ.Comparison of discrimination techniques applied to a complex data set of head injured patients (with discussion) . Journal of the Royal Statistical Society A1981; 144: 145-175 .
34.
Hand DJ , Yi K.Idiot’s Bayes - not so stupid after all ? International Statistical Review2001; 69: 385-398 .
35.
Hunt LA , Jorgensen MA.Mixture model clustering: a brief introduction to the MULTIMIX program . Australian and New Zealand Journal of Statistics1999; 40: 153-171 .
36.
Byar DP , Green SB.The choice of treatment for cancer patients based on covariate information: application to prostate cancer . Bulletin du Cancer (Paris)1980; 67: 477-490 .
