EXACT SCORE FOR TIME-SERIES MODELS IN STATE-SPACE FORM

被引：23

作者：

KOOPMAN, SJ ^{[1
]}

SHEPHARD, N ^{[1
]}

机构：

[1] UNIV OXFORD NUFFIELD COLL,OXFORD OX1 1NF,ENGLAND

来源：

BIOMETRIKA | 1992年 / 79卷 / 04期

关键词：

EM ALGORITHM; KALMAN FILTER; SMOOTHING; UNOBSERVED COMPONENT;

D O I：

10.2307/2337237

中图分类号：

Q [生物科学];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

This paper shows that the score vector for Gaussian state space models takes on a simple form which can be computed in a single pass of the Kalman filter and a smoother.

引用

页码：823 / 826

页数：4

共 7 条

[1]

[Anonymous], 1989, BAYESIAN FORECASTING

[2] SMOOTHING AND INTERPOLATION WITH THE STATE-SPACE MODEL [J].

DEJONG, P .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1989, 84 (408) :1085-1088

[3] COVARIANCES FOR SMOOTHED ESTIMATES IN STATE-SPACE MODELS [J].

DEJONG, P ;

MACKINNON, MJ .

BIOMETRIKA, 1988, 75 (03) :601-602

[4] A ONE-FACTOR MULTIVARIATE TIME-SERIES MODEL OF METROPOLITAN WAGE RATES [J].

ENGLE, R ;

WATSON, M .

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1981, 76 (376) :774-781

[5]

Gill P. E., 1981, PRACTICAL OPTIMIZATI

[6]

Harvey Andrew C., 1989, FORECASTING STRUCTUR, DOI 10.1017/CBO9781107049994

[7]

KOOPMAN SJ, 1993, IN PRESS BIOMETRIKA, V80

← 1 →