摘要
针对在传统的统计方法中,联合分析方法不能同时对大量参数进行变量估计问题,提出了贝叶斯β回归模型。该模型使用Dirichlet分布作为模型参数的先验分布,并设计相关MCMC(Markov Chain Monte Carlo)算法对模型进行拟合。通过分析将该模型应用于离散指标变量评估中,结果表明该模型对数据拟合效果好且算法收敛速度快,说明贝叶斯层次模型弥补了传统联合分析方法的缺陷,并对联合分析方法进行了优化改进。
In traditional statistical methods,the conjoint analysis method is can not estimate variables for a large number of parameters at the same time,therefore,a Bayesianβregression model is proposed.In the newly established model,the Dirichlet distribution is used as the prior distribution of the model parameters,and the relevant MCMC(Markov Chain Monte Carlo)algorithm is designed to fit the model.By analyzing the results of applying the model to the evaluation of discrete index variables,it is shown that the model has a good fitting effect on the data and the algorithm has a fast convergence speed.It shows that the Bayesian hierarchical model makes up for the defects of the traditional conjoint analysis method,and optimizes and improves the conjoint analysis method.
作者
李硕
刘贺家
刘东来
李阳
LI Shuo;LIU Hejia;LIU Donglai;LI Yang(School of Public Administration,Jilin University of Finance and Economics Changchun 130117,China;Jilin Province Accounting Association,Changchun 130021,China;Jilin Province Medical Security Management Center,Changchun 130033,China;College of Accounting,Jilin University of Finance and Economics Changchun 130117,China)
出处
《吉林大学学报(信息科学版)》
CAS
2022年第4期657-662,共6页
Journal of Jilin University(Information Science Edition)
基金
吉林省科技计划基金资助项目(20210601011FG)
吉林省自然科学基金资助项目(20190201134JC)
吉林省哲学社会科学基金资助项目(2021B78)
吉林省发展和改革委员会课题基金资助项目(吉发改投资[2017]784)。
关键词
贝叶斯层次模型
联合分析
MCMC算法
Dirichlet分布
Bayesian hierarchical model
conjoint analysis
Markov chain Monte Carlo(MCMC)algorithm
Dirichlet distribution