arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1001.2152math.STstat.TH
收藏

相关数据的预测分布的收敛速率

Rate of convergence of predictive distributions for dependent data

Patrizia Berti, Irene Crimaldi, Luca Pratelli, Pietro Rigo

摘要:

本文研究\[C_n(B)=\sqrt{n}\{μ_n(B)-P(X_{n+1}\in B\mid X_1,...,X_n)\},\]型经验过程,其中$(X_n)$是随机变量序列,$μ_n=(1/n)\sum_{i=1}^nδ_{X_i}$是经验测度.给出了$\sup_B|C_n(B)|$稳定收敛(特别是在分布上)的条件,其中$B$的取值范围是一类合适的可测集.当$(X_n)$是可交换的,或者更一般地,是条件相同分布的(在Berti等人[Ann. Probab. 32(2004)2029- 2052])。通过这样的条件,在某些相关的情况下,人们获得$\sup_B|C_n(B)|\stackrel{P}{\to}0$或甚至$\sqrt{n}\sup_B|C_n(B)|$收敛。这种类型的结果在贝叶斯统计中很有用。

英文摘要:

This paper deals with empirical processes of the type \[C_n(B)=\sqrt{n}\{μ_n(B)-P(X_{n+1}\in B\mid X_1,...,X_n)\},\] where $(X_n)$ is a sequence of random variables and $μ_n=(1/n)\sum_{i=1}^nδ_{X_i}$ the empirical measure. Conditions for $\sup_B|C_n(B)|$ to converge stably (in particular, in distribution) are given, where $B$ ranges over a suitable class of measurable sets. These conditions apply when $(X_n)$ is exchangeable or, more generally, conditionally identically distributed (in the sense of Berti et al. [Ann. Probab. 32 (2004) 2029--2052]). By such conditions, in some relevant situations, one obtains that $\sup_B|C_n(B)|\stackrel{P}{\to}0$ or even that $\sqrt{n}\sup_B|C_n(B)|$ converges a.s. Results of this type are useful in Bayesian statistics.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑