Abstract
The expectation maximization(EM) algorithm is a general iterative algorithm for the maximum-likelihood estimation(MLE) in incomplete-data problems. Dempster, Laird and Rubin(1977, henceforth DLR) showed that convergence is linear with rate proportional to the ratio of the missing information to the complete information. When a large proportion of data are missing, the speed of convergence can be very slow.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Dempster, A. P., Laird, N. M. and Rubin, D. B. (1977), Maximum likelihood estimation from incomplete data via the EM algorithm(with discussion). J. R. Stat. Soc., B39, 1–38.
Geng, Z. (1988), Multidimensional contingency tables with missing data. Communs Statist.-Theory and Meth., 17, 4137–4146.
Geng, Z., C. Asano, M. Ichimura and H. Kimura (1994), Algorithm AS 294: Decomposability and collapsibility for contingency tables with missing data. App. Statist., 43, 548–554.
Meng, X. L. (1994), On the rate of convergence of the ECM algorithm. Ann. Statist, 22, 326–339.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1996 Physica-Verlag Heidelberg
About this paper
Cite this paper
Geng, Z., Tao, F., Wan, K., Asano, C., Ichimura, M., Kuroda, M. (1996). Partial Imputation Method in the EM Algorithm. In: Prat, A. (eds) COMPSTAT. Physica-Verlag HD. https://doi.org/10.1007/978-3-642-46992-3_30
Download citation
DOI: https://doi.org/10.1007/978-3-642-46992-3_30
Publisher Name: Physica-Verlag HD
Print ISBN: 978-3-7908-0953-4
Online ISBN: 978-3-642-46992-3
eBook Packages: Springer Book Archive