Propriety of posterior distribution for dichotomous quantal response models

被引:39
作者
Chen, MH
Shao, QM
机构
[1] Worcester Polytech Inst, Dept Math Sci, Worcester, MA 01609 USA
[2] Univ Oregon, Dept Math, Eugene, OR 97403 USA
关键词
improper prior; logit model; log-log model; probit model; maximum likelihood estimate;
D O I
10.1090/S0002-9939-00-05513-1
中图分类号
O29 [应用数学];
学科分类号
070104 ;
摘要
In this article, we investigate the property of posterior distribution for dichotomous quantal response models using a uniform prior distribution on the regression parameters. Sufficient and necessary conditions for the propriety of the posterior distribution with a general link function are established. In addition, the sufficient conditions for the existence of the posterior moments and the posterior moment generating function are also obtained. Finally, the relationship between the propriety of posterior distribution and the existence of the maximum likelihood estimate is examined.
引用
收藏
页码:293 / 302
页数:10
相关论文
共 13 条
[1]  
Agresti A., 1990, Analysis of categorical data
[2]  
ALBERT A, 1984, BIOMETRIKA, V71, P1
[3]  
Chen M-H, 1998, SANKHYA A, V60, P322
[4]  
*CPLEX OPT INC, 1992, CPLEX
[5]   MAXIMUM LIKELIHOOD ESTIMATES IN EXPONENTIAL RESPONSE MODELS [J].
HABERMAN, SJ .
ANNALS OF STATISTICS, 1977, 5 (05) :815-841
[6]   ON BAYESIAN-ANALYSIS OF GENERALIZED LINEAR-MODELS USING JEFFREYS PRIOR [J].
IBRAHIM, JG ;
LAUD, PW .
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1991, 86 (416) :981-986
[7]  
McCullagh P., 2019, Generalized Linear Models
[8]  
NATARAJAN R, 1995, BIOMETRIKA, V82, P639, DOI 10.2307/2337540
[9]  
ROCKAFELLAR T., 1970, Convex Analysis
[10]  
SANTNER TJ, 1986, BIOMETRIKA, V73, P755