Limit theorems for empirical processes based on dependent data

被引:15
作者
Berti, Patrizia [1 ]
Pratelli, Luca [2 ]
Rigo, Pietro [3 ]
机构
[1] Univ Modena & Reggio Emilia, Modena, Italy
[2] Accademia Navale Livorno, Livorno, Italy
[3] Univ Pavia, I-27100 Pavia, Italy
来源
ELECTRONIC JOURNAL OF PROBABILITY | 2012年 / 17卷
关键词
Conditional identity in distribution; Empirical process; Exchangeability; Predictive measure; Stable convergence; PREDICTIVE-DISTRIBUTIONS; RANDOM-VARIABLES; CONVERGENCE; SEQUENCES;
D O I
10.1214/EJP.v17-1765
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
Let (X-n) be any sequence of random variables adapted to a filtration (G(n)). Define a(n)(.) = P(Xn+1 is an element of . vertical bar G(n)), b(n) = 1/n Sigma(n-1)(i=0) a(i), and mu(n) = 1/n Sigma(n)(i=1) delta(Xi). Convergence in distribution of the empirical processes B-n = root n (mu(n) - b(n)) and C-n = root n (mu(n) - a(n)) is investigated under uniform distance. If (X-n) is conditionally identically distributed, convergence of B-n and C-n is studied according to Meyer-Zheng as well. Some CLTs, both uniform and non uniform, are proved. In addition, various examples and a characterization of conditionally identically distributed sequences are given.
引用
收藏
页码:1 / 18
页数:18
相关论文
共 21 条
[1]  
Aldous D. J., 1977, PROB THEO RELAT FIEL, V40, P59
[2]  
[Anonymous], 2000, Sankhya, Ser. A
[3]  
[Anonymous], 1999, Cambridge Studies in Advanced Mathematics
[4]   CONDITIONALLY IDENTICALLY DISTRIBUTED SPECIES SAMPLING SEQUENCES [J].
Bassetti, Federico ;
Crimaldi, Irene ;
Leisen, Fabrizio .
ADVANCES IN APPLIED PROBABILITY, 2010, 42 (02) :433-459
[5]   Asymptotic behaviour of the empirical process for exchangeable data [J].
Berti, P ;
Pratelli, L ;
Rigo, P .
STOCHASTIC PROCESSES AND THEIR APPLICATIONS, 2006, 116 (02) :337-344
[6]   Limit theorems for a class of identically distributed random variables [J].
Berti, P ;
Pratelli, L ;
Rigo, P .
ANNALS OF PROBABILITY, 2004, 32 (3A) :2029-2052
[7]   A uniform limit theorem for predictive distributions [J].
Berti, P ;
Rigo, P .
STATISTICS & PROBABILITY LETTERS, 2002, 56 (02) :113-120
[8]  
Berti P, 2011, J APPL PROBAB, V48, P527
[9]   Rate of convergence of predictive distributions for dependent data [J].
Berti, Patrizia ;
Crimaldi, Irene ;
Pratelli, Luca ;
Rigo, Pietro .
BERNOULLI, 2009, 15 (04) :1351-1367
[10]  
Crimaldi I, 2007, LECT NOTES MATH, V1899, P203