Large sample properties of parameter estimates for periodic ARMA models

被引:75
作者
Basawa, IV [1 ]
Lund, R [1 ]
机构
[1] Univ Georgia, Athens, GA 30602 USA
关键词
least squares; maximum likelihood; periodic time series; PARMA model; ARMA model; VARMA model;
D O I
10.1111/1467-9892.00246
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
This paper studies the asymptotic properties of parameter estimates for causal and invertible periodic autoregressive moving-average (PARMA) time series models. A general limit result for PARMA parameter estimates with a moving-average component is derived. The paper presents examples that explicitly identify the limiting covariance matrix for parameter estimates from a general periodic autoregression (PAR), a first-order periodic moving average (PMA(1)), and the mixed PARMA(1,1) model. Some comparisons and contrasts to univariate and vector autoregressive moving-average sequences are made.
引用
收藏
页码:651 / 663
页数:13
相关论文
共 24 条
[1]  
[Anonymous], 1968, Probability
[2]  
Bentarzi M., 1994, J TIME SER ANAL, V15, P263, DOI DOI 10.1111/j.1467-9892.1994.tb00191.x
[3]  
Bloomfield P., 1994, Journal of Time Series Analysis, V15, P127, DOI DOI 10.1111/J.1467-9892.1994.TB00181.X
[4]  
Brockwell P. J., 1991, TIME SERIES THEORY M
[5]  
Cipra T., 1987, Journal of Time Series Analysis, V8, P293, DOI [10.1111/j.1467-9892.1987.tb00441.x, DOI 10.1111/J.1467-9892.1987.TB00441.X]
[6]   VECTOR LINEAR TIME-SERIES MODELS - CORRECTIONS AND EXTENSIONS [J].
DEISTLER, M ;
DUNSMUIR, W ;
HANNAN, EJ .
ADVANCES IN APPLIED PROBABILITY, 1978, 10 (02) :360-372
[7]   VECTOR LINEAR TIME SERIES MODELS [J].
DUNSMUIR, W ;
HANNAN, EJ .
ADVANCES IN APPLIED PROBABILITY, 1976, 8 (02) :339-364
[8]  
Fuller W.A., 1996, INTRO STAT TIME SERI, V2nd
[9]   CHARACTERIZATION OF CYCLOSTATIONARY RANDOM SIGNAL PROCESSES [J].
GARDNER, WA ;
FRANKS, LE .
IEEE TRANSACTIONS ON INFORMATION THEORY, 1975, 21 (01) :4-14
[10]  
Gladyshev E.G., 1961, Soviet. Math., V2, P385