Fast likelihood evaluation and prediction for nonstationary state space models

Piet De Jong; Singfat Chu-chun-lin

doi:10.1093/biomet/81.1.133

Fast likelihood evaluation and prediction for nonstationary state space models

Piet De Jong^*, Singfat Chu-chun-lin

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

19 Citations (Scopus)

Abstract

SUMMARY: A recursive procedure for initializing the Kalman filter is displayed. The recursion is for nonstationary state space models. The procedure imposes small computational and programming burden over and above the Kalman filter. The procedure is superior to other suggested approaches in both computational speed and general applicability. General properties of the method are investigated. Details of the initialization for the ARIMA (p,d,q) and basic structural models are considered.

Original language	English
Pages (from-to)	133-142
Number of pages	10
Journal	Biometrika
Volume	81
Issue number	1
DOIs	https://doi.org/10.1093/biomet/81.1.133
Publication status	Published - Mar 1994
Externally published	Yes

Keywords

ARIMA model
Basic structural model
Diffuse
Kalman filter
Likelihood
Nonstationarity
Prediction
State space

Access to Document

10.1093/biomet/81.1.133

Cite this

@article{4a4a81b85151402dbfdf620dd73a222c,

title = "Fast likelihood evaluation and prediction for nonstationary state space models",

abstract = "SUMMARY: A recursive procedure for initializing the Kalman filter is displayed. The recursion is for nonstationary state space models. The procedure imposes small computational and programming burden over and above the Kalman filter. The procedure is superior to other suggested approaches in both computational speed and general applicability. General properties of the method are investigated. Details of the initialization for the ARIMA (p,d,q) and basic structural models are considered.",

keywords = "ARIMA model, Basic structural model, Diffuse, Kalman filter, Likelihood, Nonstationarity, Prediction, State space",

author = "Jong, {Piet De} and Singfat Chu-chun-lin",

year = "1994",

month = mar,

doi = "10.1093/biomet/81.1.133",

language = "English",

volume = "81",

pages = "133--142",

journal = "Biometrika",

issn = "0006-3444",

publisher = "Oxford University Press",

number = "1",

}

TY - JOUR

T1 - Fast likelihood evaluation and prediction for nonstationary state space models

AU - Jong, Piet De

AU - Chu-chun-lin, Singfat

PY - 1994/3

Y1 - 1994/3

N2 - SUMMARY: A recursive procedure for initializing the Kalman filter is displayed. The recursion is for nonstationary state space models. The procedure imposes small computational and programming burden over and above the Kalman filter. The procedure is superior to other suggested approaches in both computational speed and general applicability. General properties of the method are investigated. Details of the initialization for the ARIMA (p,d,q) and basic structural models are considered.

AB - SUMMARY: A recursive procedure for initializing the Kalman filter is displayed. The recursion is for nonstationary state space models. The procedure imposes small computational and programming burden over and above the Kalman filter. The procedure is superior to other suggested approaches in both computational speed and general applicability. General properties of the method are investigated. Details of the initialization for the ARIMA (p,d,q) and basic structural models are considered.

KW - ARIMA model

KW - Basic structural model

KW - Diffuse

KW - Kalman filter

KW - Likelihood

KW - Nonstationarity

KW - Prediction

KW - State space

UR - http://www.scopus.com/inward/record.url?scp=0000063584&partnerID=8YFLogxK

U2 - 10.1093/biomet/81.1.133

DO - 10.1093/biomet/81.1.133

M3 - Article

AN - SCOPUS:0000063584

SN - 0006-3444

VL - 81

SP - 133

EP - 142

JO - Biometrika

JF - Biometrika

IS - 1

ER -

Fast likelihood evaluation and prediction for nonstationary state space models

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this