IMPROVING THE EM ALGORITHM

被引:28
作者
RAI, SN
MATTHEWS, DE
机构
[1] Statistics/Actuarial Science Dept., University of Waterloo, Waterloo
关键词
CARCINOGENICITY EXPERIMENT; EM ALGORITHM; INCOMPLETE DATA;
D O I
10.2307/2532570
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
A modification of the EM algorithm is proposed for situations in which the maximization of the ''complete data'' likelihood function does not have a closed-form solution. Self-consistency of the modified algorithm is established. Application to carcinogenicity experiments is illustrated, and the results of a simulation study comparing the original and modified versions indicate that use of the proposed modification can lead to significant computational savings.
引用
收藏
页码:587 / 591
页数:5
相关论文
共 4 条
[1]  
Cox DR, 1984, ANAL SURVIVAL DATA, pviii
[2]   MAXIMUM LIKELIHOOD FROM INCOMPLETE DATA VIA EM ALGORITHM [J].
DEMPSTER, AP ;
LAIRD, NM ;
RUBIN, DB .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL, 1977, 39 (01) :1-38
[3]   NONPARAMETRIC METHODS FOR SURVIVAL SACRIFICE EXPERIMENTS [J].
DEWANJI, A ;
KALBFLEISCH, JD .
BIOMETRICS, 1986, 42 (02) :325-341
[4]   THE DELTA-ALGORITHM AND GLIM [J].
JORGENSEN, B .
INTERNATIONAL STATISTICAL REVIEW, 1984, 52 (03) :283-300