左截断右删失数据下二项分布参数多变点的贝叶斯估计

Bayesian Estimation of Parameter of Binomial Distribution with Multiple Change Points for Left Truncated and Right Censored Data

  • 摘要: 通过添加缺损的寿命变量数据得到了左截断右删失数据下泊松分布的完全数据似然函数.给出了变点位置和其它参数的满条件分布.利用Gibbs抽样与Metropolis-Hastings算法相结合的MCMC方法对各参数的满条件分布分别进行了抽样.详细介绍了MCMC方法的实施步骤.得到了参数的Gibbs样本,把Gibbs样本的均值作为各参数的贝叶斯估计.随机模拟试验的结果表明各参数贝叶斯估计的精度都较高.

     

    Abstract: By filling in the missing data of the life variable, the complete-data likelihood function of binomial distribution for left truncated and right censored data is obtained. The full conditional distributions of change-point positions and other parameters are given. Every parameter is sampled from the full conditional distributions respectively, using MCMC method of Gibbs sampling together with Metropolis-Hastings algorithm. The implementation steps of MCMC method are introduced in detail. Gibbs samples of the parameters are obtained, and the means of Gibbs samples are taken as Bayesian estimations of the parameters. The random simulation test results show that Bayesian estimations of the parameters is fairly accurate.

     

/

返回文章
返回