Stochastic versions of the em algorithm: an experimental study in the mixture case
- 1 November 1996
- journal article
- research article
- Published by Taylor & Francis in Journal of Statistical Computation and Simulation
- Vol. 55 (4) , 287-314
- https://doi.org/10.1080/00949659608811772
Abstract
We compare three different stochastic versions of the EM algorithm: The Stochastic EM algorithm (SEM), the “Simulated Annealing” EM algorithm (SAEM) and the Monte Carlo EM algorithm (MCEM). We focus particularly on the mixture of distributions problem. In this context, we investigate the practical behaviour of these algorithms through intensive Monte Carlo numerical simulations and a real data study. We show that, for some particular mixture situations, the SEM algorithm is almost always preferable to the EM and “simulated annealing” versions SAEM and MCEM. For some severely overlapping mixtures, however, none of these algorithms can be confidently used. Then, SEM can be used as an efficient data exploratory tool for locating significant maxima of the likelihood function. In the real data case, we show that the SEM stationary distribution provides a contrasted view of the loglikelihood by emphasizing sensible maxima.Keywords
This publication has 14 references indexed in Scilit:
- Almost sure convergence of a class of stochastic algorithmsStochastic Processes and their Applications, 1994
- Comparison of the mixture and the classification maximum likelihood in cluster analysisJournal of Statistical Computation and Simulation, 1993
- Asymptotic properties of a stochastic EM Algorithm for estimating mixing proportionsCommunications in Statistics. Stochastic Models, 1993
- Estimation of parameters in hidden Markov modelsPhilosophical Transactions A, 1991
- A Monte Carlo Implementation of the EM Algorithm and the Poor Man's Data Augmentation AlgorithmsJournal of the American Statistical Association, 1990
- Some recent research in the analysis of mixture distributionsStatistics, 1990
- Classification and Mixture Approaches to Clustering via Maximum LikelihoodJournal of the Royal Statistical Society Series C: Applied Statistics, 1989
- The Calculation of Posterior Distributions by Data AugmentationJournal of the American Statistical Association, 1987
- Likelihood Estimation with Normal Mixture ModelsJournal of the Royal Statistical Society Series C: Applied Statistics, 1985
- Mixture Densities, Maximum Likelihood and the EM AlgorithmSIAM Review, 1984