Summary
We discuss a special class of stochastic versions of the EM algorithms. The advantage of the single imputation procedure in non-exponential family applications is highlighted. We prove that ergodic properties of the stochastic algorithms are dependent not on the multiplicity of the imputation scheme but rather on the stability of the deterministic component of an underlying stochastic difference equation.
Similar content being viewed by others
References
Celeux, G. and Diebolt, J. (1985), The SEM algorithm: a probabilistic teacher algorithm derived from the EM algorithm for the mixture problem, Comp. Statist. Quart., 2, 73–82.
Chauveau, D. and Diebolt, J. (1999), An automatic stopping rule for MCMC convergence assessment, Comp. Statist., 14, 419–442.
Chan, K. (1990), Deterministic stability, stochastic stability and ergodicity, in: Tong, H., Non-linear Time Series (Oxford University Press, New York), pp. 448.
Delyon, B., Lavielle, M. and Moulines, E. (1999), Convergence of a stochastic approximation version of the EM algorithm, Ann. Statist., 27, 94–128.
Dempster, A., Laird, N., and Rubin, D. (1977), Maximum likelihood from incomplete data via the EM algorithm (with discussion), J. R. Statist. Soc., B39, 1–38.
Diebolt, J., and Ip, E.H. (1996), Stochastic EM: method and application, in: Gilks, W., Richardson, S., and Spiegelhalter, D. J., eds. Markov Chain Monte Carlo in Practice (Chapman and Hall, London) pp. 259–273.
Kifer, Y. (1988), Random Perturbations of Dynamical Systems(Birkhauser, Boston).
Lehmann, E. (1983). Theory of Point Estimation (Wadsworth and Brooks/(California).
Meyn, S. P., and Tweedie, R. L. (1993), Markov Chain and Stochastic Stability (Springer-Verlag, New York).
Ruud, P.A. (1991), Extensions of estimation methods using the EM algorithm, J. Economet., 49, 305–341.
Tweedie, R. (1975), Sufficient conditions for ergodicity and recurrence of Markov chain on a general state space, Stoch. Proc. Appl., 3, 385–403.
Tweedie, R. (1983), The existence of moments for stationary Markov chains, J. Appl. Prob., 20, 191–196.
Wang, N. and Robins, J.M. (1998), Large-sample theory for parametric multiple imputation procedures, Biometrika, 85, 699–704.
Wei, G.C.G. and Tanner, M.A. (1990), A Monte Carlo implementation of the EM algorithm and the poor man’s data augmentation algorithms, J. Am. Statist. Assoc. 85, 699–704.
Acknowledgement
This paper is a modified version of a chapter from the author’s doctoral dissertation. The author thanks both Jean Diebolt and Ingram Olkin for their guidance, and for suggestions to this paper.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Ip, E.H. On Single Versus Multiple Imputation for a Class of Stochastic Algorithms Estimating Maximum Likelihood. Computational Statistics 17, 517–524 (2002). https://doi.org/10.1007/s001800200124
Published:
Issue Date:
DOI: https://doi.org/10.1007/s001800200124