摘要
通过结合spike and slab先验和非参数似然函数,提出了部分区间删失数据下比例风险模型的贝叶斯变量选择.引入泊松与0-1潜变量简化似然,进而运用EM算法求出了各个参数的最大后验估计.通过模拟和实证验证了该方法的有效性.
By combining spike and slab priors and non-parametric likelihood functions,a Bayesian variable selection for proportional hazards models with partially interval-censored data is proposed.Poisson and 0-1 latent variables are introduced to simplify the likelihood,and then the EM algorithm is used to obtain the maximum a posteriori estimate of each parameter.The effectiveness of the method is verified by simulation and empirical.
作者
李纯净
赵昱榕
张淼
LI Chun-jing;ZHAO Yu-rong;ZHANG Miao(School of Mathematics and Statistics,Changchun University of Technology,Changchun 130012,China)
出处
《东北师大学报（自然科学版）》
CAS
北大核心
2023年第3期37-44,共8页
Journal of Northeast Normal University(Natural Science Edition)
基金
国家自然科学基金青年基金资助项目(11901053)
吉林省科技厅重大科技专项基金资助项目(20210301038GX)
吉林省科技厅科技发展规划项目(20210101149).
关键词
部分区间删失
比例风险模型
潜变量
贝叶斯变量选择
EM算法
partial interval censoring
proportional hazards model
latent variable
Bayesian variable selection
EM algorithm
