Determine the number of components in a mixture model by the extended KS test

Pattern Recognition Letters

Volumn 25, Issue 2, 2004, Pages 211-216

  Zhang, Ming Heng ^a   Cheng, Qian Sheng ^b  

^a SHANGHAI UNIVERSITY OF FINANCE AND ECONOMICS   (China)

^b PEKING UNIVERSITY   (China)

Author keywords

EM procedure; KS test; Mixture models; Parallel computation

Indexed keywords

COMPONENTS; COMPUTER SIMULATION;

MIXTURE MODELS;

PATTERN RECOGNITION;

PARALLEL COMPUTING;

EID: 0348108136     PISSN: 01678655     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.patrec.2003.10.002     Document Type: Article

References (16)

1. Aitkin M. Rubin D.B. Estimation and hypothesis testing in finite mixture models J. Roy. Statist. Soc. Ser. B 47 1 1985 67-75
2. Biernack C. Celeux G. Govaert G. An improvement of the NEC criterion for assessing the number of clusters in a mixture model Pattern Recognition Lett. 20 1996 272-276
3. Biernack C. Celeux G. Govaert G. Assessing a mixture model for clustering with the integrated completed likelihood IEEE Trans. Pattern Anal. Machine Intell. 7 22 2000 719-725
4. Cabana A. Cabana E.M. Transformed empirical processes and modified Kolmogonov-Smironov tests for multivariable distributions Ann. Statist. 25 6 1997 2388-2409
5. Celeux G. An entropy criterion for assessing the number of clusters in a mixture model J. Classification 13 1996 195-212
6. Dempster A.P. Laird N.M. Rubin D.B. Maximum likelihood from incomplete data via the EM algorithm (with discussion) J. Roy. Statist. Soc. Ser. B 39 1977 1-38
7. Drew J.H. Glen A.G. Leemis L.M. Computing the cumulative distribution of the Kolmogorov-Smirnov statistic Comput. Statist. Data Anal. 34 2000 1-15
8. Everitt B.S. Hand D.J. Finite Mixture Distributions 1981 Chapman - Hall London
9. McLachlan G.J. Krishnan T. The EM algorithm and extensions 1997 Wiley New York
10. Mengersen K.L. Robert C.P. Testing for mixtures: a Bayesian entropic approach (with discussion) Bayesian Statist. 5 1996 255-276
11. Quinn B.G. McLachlan G.J. Hjort N.L. A Note on the Aitkin-Rubin approach to testing in mixture models J. Roy. Statist. Soc. Ser. B 49 2 1987 311-314
12. Rissanen J. Minimum description length principle Encyclopedia Statist. Sci. 5 1985 523-527
13. Rivals I. On cross-validation for model selection Neural Comput. 11 4 1999 863-870
14. Schwarz G. Estimating the dimension of a model Ann. Statist. 6 2 1978 461-464
15. Vapnik V.N. The nature of statistical learning theory 2000 Spinger-Verlag New York
16. Xu L. Jordan M.I. On convergence properties of the EM algorithm for Gaussian mixtures Neural Comput. 8 1996 129-151