摘要
利用泊松分布和二项分布的关系,通过引入潜在变量得到了泊松过程单变点模型比较简单的似然函数.得到了未知参数的满条件分布,对满条件分布进行了Gibbs抽样,基于Gibbs样本对参数进行估计.随机模拟试验的结果表明贝叶斯估计的精度较高.
By introducing a latent variable, the simple likelihood function of Poisson process with a change-point is obtained according to the relationship of Poisson distribution to binomial distribution. Then the full conditional distributions of unknown parameters are obtained, Gibbs sampling is performed for them, and the parameters are estimated based on the Gibbs sample. The result of random simulation test shows that the accuracy of Bayesian estimation is comparatively high.
出处
《兰州理工大学学报》
CAS
北大核心
2017年第2期163-166,共4页
Journal of Lanzhou University of Technology
基金
河南省科技攻关计划(162102310384)
河南省高等学校重点科研项目(16A110001)
关键词
泊松过程
变点
可加性
MCMC方法
满条件分布
Poisson process
change-point
additivity
MCMC method
full conditional distribution