ESTIMATION PROCEDURES FOR STRUCTURAL TIME-SERIES MODELS

被引：140

作者：

HARVEY, AC ^{[1
]}

PETERS, S ^{[1
]}

机构：

[1] MONASH UNIV,DEPT ECONOMETR,CLAYTON,VIC 3168,AUSTRALIA

来源：

JOURNAL OF FORECASTING | 1990年 / 9卷 / 02期

关键词：

EM algorithm; Forecasting; Kalman filter; Stochastic trend; Structural time series model; Unobserved components model;

D O I：

10.1002/for.3980090203

中图分类号：

F [经济];

学科分类号：

02 ;

摘要：

A univariate structural time series model based on the traditional decomposition into trend, seasonal and irregular components is defined. A number of methods of computing maximum likelihood estimators are then considered. These include direct maximization of various time domain likelihood function. The asymptotic properties of the estimators are given and a comparison between the various methods in terms of computational efficiency and accuracy is made. The methods are then extended to models with explanatory variables. Copyright © 1990 John Wiley & Sons, Ltd.

引用

页码：89 / 108

页数：20

共 42 条

[1]

ANDERSON BDO, 1980, J ECONOMETRICS, V13, P159

[2] ESTIMATION, FILTERING, AND SMOOTHING IN STATE-SPACE MODELS WITH INCOMPLETELY SPECIFIED INITIAL CONDITIONS [J].