Moderate deviation principle in nonlinear bifurcating autoregressive models

被引:2
作者
Penda, S. Valere Bitseki [1 ]
Olivier, Adelaide [2 ]
机构
[1] Univ Bourgogne Franche Comte, IMB, CNRS, UMR 5584, 9 Ave Alain Savary, F-21078 Dijon, France
[2] Univ Paris Saclay, Univ Paris Sud, CNRS, Lab Math Orsay, F-91405 Orsay, France
关键词
Bifurcating Markov chain; Binary tree; Bifurcating autoregressive process; Nonparametric estimation; Nadaraya-Watson estimator; Moderate deviation principle; MARKOV-CHAINS; LIMIT-THEOREMS; INEQUALITIES;
D O I
10.1016/j.spl.2018.02.037
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
Recently, nonparametric techniques have been proposed to study bifurcating autoregressive processes. One can build Nadaraya-Watson type estimators of the two autoregressive functions as in Bitseki Penda et al. (2017) and Bitseki Penda and Olivier (2017). In the present work, we prove moderate deviation principle for these estimators. (C) 2018 Elsevier B.V. All rights reserved.
引用
收藏
页码:20 / 26
页数:7
相关论文
共 18 条