Relationship Between a Central Limit Theorem and Hotelling's \(T^2\)-Statistic in the Context of the Stochastic EM Algorithm Used in Mixture Analysis

Authors

DOI:

https://doi.org/10.26713/cma.v12i3.1653

Keywords:

Stochastic EM, Stationary process, Hotelling's statistic, Asymptotic distribution

Abstract

In earlier research the asymptotic distribution of a test statistic, that uses the algebraic representation of Hotelling's \(T^2\) and is pertaining to a process generated from the Stochastic EM (SEM) algorithm, was established in order to assess the performance of the EM algorithm in the estimation of the number of components in finite mixtures; theory concerning the distribution of \(T^2\) was based on a regularity assumption stating that the vector random process generated from SEM is normally distributed. In the present paper a central limit theorem and some theory concerning second order moments are used in order to investigate corresponding results obtained in case the process is generated from the stationary state of SEM without making any assumption of normality. A comparison between our findings and usual asymptotic theory for independently distributed vector random variables is also provided.

Downloads

Download data is not yet available.

References

T. W. Anderson, An Introduction to Multivariate Statistical Analysis, 2nd ed., Wiley, New York (1984).

G. Celeux, Validity tests in cluster analysis using a probabilistic teacher algorithm. Compstat 86, Physica-Verlag (1986), 163-168, DOI: 10.1007/978-3-642-46890-2.

G. Celeux, Reconnaissance de Mélanges de Densités de Probabilité et Applications í la Validation des Résultats en Classification, Ph. D. Thesis, University Paris 9-Dauphine (1987).

G. Celeux and J. Diebolt, The SEM algorithm: a probabilistic teacher algorithm derived from the EM algorithm for the mixture problem. Computational Statistics Quarterly 2 (1985), 73-82.

G. Celeux and J. Diebolt, Etude du comportement asymptotique d'un algorithme d'apprentissage probabiliste pour les mélanges de lois de probabilité, Research Report RR-0563, INRIA, inria-00075991 (1986), https://hal.inria.fr/inria-00075991.

G. Celeux and J. Diebolt, A random imputation principle: the stochastic EM algorithm, Research Report RR-0901, INRIA, inria-00075655 (1988), https://hal.inria.fr/inria-00075655.

A. Polymenis, A note on a validity test using the stochastic EM algorithm in order to assess the number of components in a finite mixture model, Statistics 42(3) (2008), 261-274, DOI: 10.1080/02331880701829922.

A. Polymenis, Asymptotic results for a stationary random process generated by the stochastic EM algorithm in mixture analyses, Journal of Statistics and Management Systems 21(2) (2018), 251-260, DOI: 10.1080/09720510.2017.1418211.

M. B. Priestley, Spectral analysis of time series. Vol. I - Univariate Series, Academic Press (1981).

R. A. Redner and H. F. Walker, Mixture densities, maximum likelihood and the EM algorithm, SIAM Review 26, (1984), 195-239, https://www.jstor.org/stable/2030064.

D. M. Titterington., A. F. M. Smith and U. E. Makov, Statistical Analysis of Finite Mixture Distributions, Wiley, New York (1985).

Downloads

Published

30-09-2021
CITATION

How to Cite

Polymenis, A. (2021). Relationship Between a Central Limit Theorem and Hotelling’s \(T^2\)-Statistic in the Context of the Stochastic EM Algorithm Used in Mixture Analysis. Communications in Mathematics and Applications, 12(3), 749–754. https://doi.org/10.26713/cma.v12i3.1653

Issue

Section

Research Article