EXACT LIKELIHOOD EVALUATION IN A MARKOV MIXTURE MODEL FOR TIME-SERIES OF SEIZURE COUNTS

被引:18
|
作者
LE, ND
LEROUX, BG
PUTERMAN, ML
机构
[1] HLTH & WELF CANADA,OTTAWA K1A 0L2,ONTARIO,CANADA
[2] UNIV BRITISH COLUMBIA,FAC COMMERCE,VANCOUVER V6T 1Z2,BC,CANADA
关键词
COMPUTATION; EM ALGORITHM; HIDDEN MARKOV MODEL; PARAMETER ESTIMATION; SEIZURE DATA;
D O I
10.2307/2532758
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
This paper provides an alternative to Albert's (1991, Biometrics 47, 1371-1381) approximation to the E-step when using the EM algorithm for parameter estimation in Markov mixture models. Use of a recursive algorithm of Baum et al. (I 970, Annals of Mathematical Statistics 41, 164-17 1) results in exact evaluation of the likelihood, optimal parameter estimates, and very efficient computation. Applications to time series of seizure counts and fetal movements clearly show the advantages of this exact approach.
引用
收藏
页码:317 / 323
页数:7
相关论文
共 50 条