ANALYSIS OF TIME-SERIES SUBJECT TO CHANGES IN REGIME
ANALYSIS OF TIME-SERIES SUBJECT TO CHANGES IN REGIME
复制标题
DOI：
10.1016/0304-4076(90)90093-9
复制
发表时间：
1990-07-01
影响因子：
6.3
通讯作者：
HAMILTON, JD
中科院分区：
文献类型：
--
作者：
HAMILTON, JD
本文介绍了一种EM算法获得最大似然估计的过程中的自回归参数的离散移位，与移位本身建模为一个离散值马尔可夫过程的结果。EM算法的简单性允许潜在的应用程序的方法，大型矢量系统。
This paper introduces an EM algorithm for obtaining maximum likelihood estimates of parameters for processes subject to discrete shifts in autoregressive parameters, with the shifts themselves modeled as the outcome of a discrete-valued Markov process. The simplicity of the EM algorithm permits potential application of the approach to large vector systems.