Abstract
A faster alternative to the EM algorithm in finite mixture distributions is described, which alternates EM iterations with Gauss-Newton iterations using the observed information matrix. At the expense of modest additional analytical effort in obtaining the observed information, the hybrid algorithm reduces the computing time required and provides asymptotic standard errors at convergence. The algorithm is illustrated on the two-component normal mixture.
Similar content being viewed by others
References
Aitkin, M. (1980) Mixture applications of the EM algorithm in GLIM. In COMPSTAT 1980. Physica-Verlag, Vienna.
Dempster, A. P., Laird, N. M. and Rubin, D. A. (1977) Maximum likelihood estimation from incomplete data via the EM algorithm (with Discussion). J. Roy. Statist. Soc. B, 39, 1–38.
Everitt, B. S. (1984) Maximum likelihood estimation of the parameters in a mixture of two univariate normal distributions: a comparison of different algorithms. The Statistician, 33, 205–15.
Louis, T. A. (1982) Finding the observed information when using the EM algorithm. J. Roy. Statist. Soc. B, 44, 226–33.
Meilijson, I. (1989) A fast improvement to the EM algorithm on its own terms. J. Roy. Statist. Soc. B, 51, 127–38.
McLachlan, G. J. and Basford, K. (1988) Mixture Models: Inference and Applications to Clustering. Dekker, New York.
Meng, X.-L. and Rubin, D. R. (1991) Using EM to obtain asymptotic variance-covariance matrices: the SEM algorithm. J. Amer. Statist. Assoc., 86, 899–909.
Redner, R. A. and Walker, H. F. (1984) Mixture densities, maximum likelihood and the EM algorithm. SIAM Review, 26, 195–239.
Titterington, D. M., Smith, A. F. M. and Makov, U. E. (1985) Statistical Analysis of Finite Mixture Distributions. Wiley, Chichester.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Aitkin, M., Aitkin, I. A hybrid EM/Gauss-Newton algorithm for maximum likelihood in mixture distributions. Stat Comput 6, 127–130 (1996). https://doi.org/10.1007/BF00162523
Issue Date:
DOI: https://doi.org/10.1007/BF00162523