1999
DOI: 10.1016/s0304-4149(99)00027-7
|View full text |Cite
|
Sign up to set email alerts
|

Innovations algorithm for periodically stationary time series

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
72
0
3

Year Published

2008
2008
2016
2016

Publication Types

Select...
5
1

Relationship

1
5

Authors

Journals

citations
Cited by 23 publications
(75 citation statements)
references
References 21 publications
0
72
0
3
Order By: Relevance
“…Estimation of time series regression models are discussed extensively in the literature for a range of models. For example Kedem et al (2002) discuss the estimation for a class of generalized linear time series models and Tesfaye et al (2006) utilizes the "innovation" algorithm developed in Anderson et al (1999) to apply PARMA models to river flow modeling in Fraser River in British Columbia. Since none of these methods are directly applicable to our method in which both the autoregressive coefficients and the volatility vary with time (in a non-linear fashion), below we discuss a simple iterative estimation method which works very efficiently both in simulations and our data analysis.…”
Section: Estimationmentioning
confidence: 99%
“…Estimation of time series regression models are discussed extensively in the literature for a range of models. For example Kedem et al (2002) discuss the estimation for a class of generalized linear time series models and Tesfaye et al (2006) utilizes the "innovation" algorithm developed in Anderson et al (1999) to apply PARMA models to river flow modeling in Fraser River in British Columbia. Since none of these methods are directly applicable to our method in which both the autoregressive coefficients and the volatility vary with time (in a non-linear fashion), below we discuss a simple iterative estimation method which works very efficiently both in simulations and our data analysis.…”
Section: Estimationmentioning
confidence: 99%
“…In practice, a model selection criterion such as AIC or BIC is used to choose the appropriate order of the model (Franses, 1996). Estimation is achieved by computing the exact Gaussian likelihood of PARMA models (Anderson et al, 1999;Lund and Basawa, 2000;Basawa and Lund, 2001). …”
Section: Periodic Arma Modelsmentioning
confidence: 99%
“…. , −1, then for a causal PARMA (p, q) process the covariance matrix k,i is non-singular for every k 1 and each i. Anderson et al [5] show that if EX t = 0 and k,i is nonsingular for each k 1, then the one-step predictorsX i+k , k 0, and their mean-square errors v k,i , k 1, are given by…”
Section: The Innovations Algorithmmentioning
confidence: 99%
“…An important class of stochastic models for describing periodically stationary time series are the periodic ARMA models, in which the model parameters are allowed to vary with the season. Periodic ARMA models are developed by many authors including [1,2,[4][5][6][7]20,[22][23][24]26,28,30,31,[33][34][35][36][37][38][39][40][41].…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation