BAYESIAN ASYMPTOTICS WITH MISSPECIFIED MODELS

被引:18
|
作者
De Blasi, Pierpaolo [1 ,2 ]
Walker, Stephen G. [3 ]
机构
[1] Univ Turin, Dept Econ & Stat, I-10134 Turin, Italy
[2] Coll Carlo Alberto, Moncalieri Torino, Italy
[3] Univ Kent, Inst Math Stat & Actuarial Sci, Canterbury CT2 7NZ, Kent, England
基金
欧洲研究理事会;
关键词
Asymptotics; consistency; misspecified model; GAUSSIAN PROCESS PRIORS; DENSITY-ESTIMATION; POSTERIOR DISTRIBUTIONS; CONSISTENCY; INFORMATION; INCORRECT; MIXTURES; BEHAVIOR;
D O I
10.5705/ss.2010.239
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
In this paper, we study the asymptotic properties of a sequence of posterior distributions based on an independent and identically distributed sample and when the Bayesian model is misspecified. We find a sufficient condition on the prior for the posterior to accumulate around the densities in the model closest in the Kullback-Leibler sense to the true density function. Examples are presented.
引用
收藏
页码:169 / 187
页数:19
相关论文
共 50 条