Finite Sample Bernstein – von Mises Theorem for Semiparametric Problems

[摘要] The classical parametric and semiparametric Bernstein – von Mises (BvM) results are reconsidered in a non-classical setup allowing finite samples and model misspecification. In the case of a finite dimensional nuisance parameter we obtain an upper bound o

[学科分类] 统计和概率

[关键词] prior;posterior;Bayesian inference;semiparametric;critical dimension