Choosing initial values for the EM algorithm for finite mixtures

Authors:
Dimitris Karlis;Evdokia Xekalaki
Affiliations:
Department of Statistics, Athens University of Economics and Business, 76 Patision St., 10434, Athens, Greece;Department of Statistics, Athens University of Economics and Business, 76 Patision St., 10434, Athens, Greece
Venue:
Computational Statistics & Data Analysis
Year:
2003

Citing 3
Cited 8

Testing for the number of components in a mixture of normal distributions using moment estimators

Computational Statistics & Data Analysis
Measuring the relative effectiveness of moment estimators as starting values in maximizing likelihoods

Computational Statistics & Data Analysis
Aitken-based acceleration methods for assessing convergence of multilayer neural networks

IEEE Transactions on Neural Networks

Editorial: recent developments in mixture models

Computational Statistics & Data Analysis
Recent asymptotic results in testing for mixtures

Computational Statistics & Data Analysis
Genetic algorithms in partitional clustering: a comparison

NN'10/EC'10/FS'10 Proceedings of the 11th WSEAS international conference on nural networks and 11th WSEAS international conference on evolutionary computing and 11th WSEAS international conference on Fuzzy systems
Initializing the EM algorithm in Gaussian mixture models with an unknown number of components

Computational Statistics & Data Analysis
Computational aspects of fitting mixture models via the expectation-maximization algorithm

Computational Statistics & Data Analysis
Preliminary estimators for a mixture model of ordinal data

Advances in Data Analysis and Classification
Variational learning of finite Dirichlet mixture models using component splitting

Neurocomputing
Finite mixtures of multivariate skew t-distributions: some recent and new results

Statistics and Computing

Quantified Score

Hi-index	0.03

Visualization

Abstract

The EM algorithm is the standard tool for maximum likelihood estimation in finite mixture models. The main drawbacks of the EM algorithm are its slow convergence and the dependence of the solution on both the stopping criterion and the initial values used. The problems referring to slow convergence and the choice of a stopping criterion have been dealt with in literature and the present paper deals with the initial value problem for the EM algorithm. The aim of this paper is to compare several methods for choosing initial values for the EM algorithm in the case of finite mixtures as well as to propose some new methods based on modifications of existing ones. The cases of finite normal mixtures with common variance and finite Poisson mixtures are examined through a simulation study.