标题:
正态分布下多个方差转变点的检测与方法探讨A Method of Detecting Multiple Change Point for Normal Distribution Process
作者:
沈卉卉
关键字:
转变点, 贝叶斯方法, 极大似然方法, 先验分布, 似然密度函数Change Point, Bayesian Method, Maximum Likelihood Method, Prior Distribution, Likelihood
Density Function
期刊名称:
《Advances in Applied Mathematics》, Vol.5 No.3, 2016-08-15
摘要:
经济系统数学模型中含有多个转变点的结构模型问题,本文对在均值相同情况下,方差多个转变点的检测方法采取的是将贝叶斯方法和极大似然方法结合起来,利用贝叶斯方法消去多余参数,极大似然方法可以回避转变点个数的先验分布信息未知的问题,给出有效的检测方法。
The problem of structure model occurs multiple change points in the economic system of mathe-matical models. In this paper, we give the detection method for change point problems about the variance changes. We combine the Bayesian method with the maximum likelihood method on the detection about the variance multiple change points in the same mean. The elimination extra pa-rameters can make use of Bayesian method; the maximum likelihood method can avoid the un-known problems of the prior distribution information of the change points number. It is a practical method.