论文信息 - THE EMMIX ALGORITHM FOR THE FITTING OF MIXTURES OF NORMAL AND t-COMPONENTS

THE EMMIX ALGORITHM FOR THE FITTING OF MIXTURES OF NORMAL AND t-COMPONENTS

We consider the tting of normal mixture models to multivariate data, using maximum likelihood via the EM algorithm. This approach requires the initial speciication of an initial estimate of the vector of unknown parameters, or equivalently, of an initial clas-siication of the data with respect to the components of the mixture model under t. We describe an algorithm called EMMIX that automatically undertakes this tting, including the provision of suitable initial values if not supplied by the user. The EMMIX algorithm has several options, including the option to carry out a resampling-based test for the number of components in the mixture model.

K. Basford | D. Peel | P. AdamsDepartment

[1] A. Raftery,et al. Nearest-Neighbor Clutter Removal for Estimating Features in Spatial Point Processes , 1998 .

[2] A. Raftery,et al. Detecting features in spatial point processes with clutter via model-based clustering , 1998 .

[3] Adrian E. Raftery,et al. How Many Clusters? Which Clustering Method? Answers Via Model-Based Cluster Analysis , 1998, Comput. J..

[4] Adrian E. Raftery,et al. Linear flaw detection in woven textiles using model-based clustering , 1997, Pattern Recognit. Lett..

[5] Dominique Haughton,et al. Packages for estimating finite mixtures : A review , 1997 .

[6] G. McLachlan,et al. The EM algorithm and extensions , 1996 .

[7] Peter C. Cheeseman,et al. Bayesian Classification (AutoClass): Theory and Results , 1996, Advances in Knowledge Discovery and Data Mining.

[8] R. Tibshirani,et al. Discriminant Analysis by Gaussian Mixtures , 1996 .

[9] David L. Dowe,et al. Intrinsic classification by MML - the Snob program , 1994 .

[10] A. Raftery,et al. Model-based Gaussian and non-Gaussian clustering , 1993 .

[11] D. N. Geary. Mixture Models: Inference and Applications to Clustering , 1989 .

[12] Geoffrey J. McLachlan,et al. Mixture models : inference and applications to clustering , 1989 .

[13] G. McLachlan. On Bootstrapping the Likelihood Ratio Test Statistic for the Number of Components in a Normal Mixture , 1987 .