机构:
Chinese Univ Hong Kong, Dept Stat, Hong Kong, Peoples R ChinaChinese Univ Hong Kong, Dept Stat, Hong Kong, Peoples R China
Chan, Ngai Hang
[1
]
Ng, Wai Leong
论文数: 0引用数: 0
h-index: 0
机构:
Hang Seng Univ Hong Kong, Dept Math Stat & Insurance, Hong Kong, Peoples R ChinaChinese Univ Hong Kong, Dept Stat, Hong Kong, Peoples R China
Ng, Wai Leong
[2
]
Yau, Chun Yip
论文数: 0引用数: 0
h-index: 0
机构:
Chinese Univ Hong Kong, Dept Stat, Hong Kong, Peoples R ChinaChinese Univ Hong Kong, Dept Stat, Hong Kong, Peoples R China
Yau, Chun Yip
[1
]
Yu, Haihan
论文数: 0引用数: 0
h-index: 0
机构:
Iowa State Univ, Dept Stat, Ames, IA USAChinese Univ Hong Kong, Dept Stat, Hong Kong, Peoples R China
Yu, Haihan
[3
]
机构:
[1] Chinese Univ Hong Kong, Dept Stat, Hong Kong, Peoples R China
[2] Hang Seng Univ Hong Kong, Dept Math Stat & Insurance, Hong Kong, Peoples R China
[3] Iowa State Univ, Dept Stat, Ames, IA USA
来源:
ANNALS OF STATISTICS
|
2021年
/
49卷
/
04期
关键词:
Bayes-type estimator;
confidence interval;
double-sided random process;
piecewise stationary time series;
structural break;
BOOTSTRAP;
GARCH;
CALIBRATION;
D O I:
10.1214/20-AOS2039
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:
This paper establishes asymptotic theory for optimal estimation of change points in general time series models under alpha-mixing conditions. We show that the Bayes-type estimator is asymptotically minimax for change-point estimation under squared error loss. Two bootstrap procedures are developed to construct confidence intervals for the change points. An approximate limiting distribution of the change-point estimator under small change is also derived. Simulations and real data applications are presented to investigate the finite sample performance of the Bayes-type estimator and the bootstrap procedures.