Asymptotic distribution of the estimated parameters of an ARMA(p, q) process with mixing innovations

被引:0
|
作者
Bhattacharya, Sankha [1 ]
Sen Roy, Sugata [2 ]
机构
[1] RKMR Coll, Narendrapur 700103, India
[2] Univ Calcutta, Dept Stat, Kolkata 700019, W Bengal, India
关键词
ARMA process; explosive roots; phi-mixing errors; asymptotic distribution; STOCHASTIC DIFFERENCE-EQUATIONS; MODELS;
D O I
10.1214/14-BJPS237
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
In this paper, we consider an ARMA(p, q) model with stationary, phi-mixing error variables having uniformly bounded fourth-order moments. Both the autoregressive and moving average components of the model involve stable and explosive roots. Estimating the autoregressive parameters using the instrumental variable technique and the moving average parameters using a derived autoregressive process, we derive the asymptotic distribution of the estimators.
引用
收藏
页码:640 / 655
页数:16
相关论文
共 39 条