On parameter estimation of threshold autoregressive models

被引：8
作者：
Ngai Hang Chan
Yury A. Kutoyants
机构：
[1] Department of Statistics, Chinese University of Hong Kong, Shatin, NT
[2] Laboratoire de Statistique et Processus, Université du Maine
来源：
Statistical Inference for Stochastic Processes | 2012年 / 15卷 / 1期
关键词：
Bayesian estimator; Compound Poisson process; Continuous-time diffusion; Limit distribution; Limit likelihood ratio; Nonlinear threshold models;
D O I：
10.1007/s11203-011-9064-0
中图分类号：
学科分类号：
摘要：
This paper studies the threshold estimation of a TAR model when the underlying threshold parameter is a random variable. It is shown that the Bayesian estimator is consistent and its limit distribution is expressed in terms of a limit likelihood ratio. Furthermore, convergence of moments of the estimators is also established. The limit distribution can be computed via explicit simulations from which testing and inference for the threshold parameter can be conducted. The obtained results are illustrated with numerical simulations. © 2011 Springer Science+Business Media B.V.
引用
收藏
页码：81 / 104
页数：23
相关论文
共 18 条
[1]  
Bradley R.C., Introduction to Strong Mixing Conditions, (2007)
[2]  
Brockwell R.J., On continuous time threshold ARMA processes, J Stat Plan Inference, 39, pp. 291-304, (1994)
[3]  
Chan K.S., Consistency and limiting distribution of the LSE of a TAR, Ann Stat, 21, pp. 520-533, (1993)
[4]  
Chan K.S., Tong H., A note on certain integral equations associated with nonlinear time series analysis, Probab Theory Relat Fields, 73, pp. 153-159, (1986)
[5]  
Chan K.S., Tong H., A note on embedding a discrete parameter ARMA model in a continuous parameter ARMA model, J Time Ser Anal, 8, pp. 277-281, (1987)
[6]  
Chen R., Tsay R., On the ergodicity of TAR(1) processes, Ann Appl Probab, 1, pp. 613-634, (1991)
[7]  
Dedeker J., Doukhan P., A new covariance inequality and applications, Stoch Process Appl, 106, pp. 63-80, (2003)
[8]  
Doukhan P., Mixing, (1994)
[9]  
Fan J., Yao Q., Nonlinear Time Series: Nonparametric and Parametric Methods, (2003)
[10]  
Geweke J., Terui N., Bayesian threshold autoregressive models for nonlinear time series, J Time Ser Anal, 14, 5, pp. 441-454, (1993)
12