Component extraction analysis of multivariate time series

被引：2

作者：

Akman, I

DeGooijer, JG

机构：

[1] MIDDLE EAST TECH UNIV,DEPT COMP ENGN,ANKARA 06531,TURKEY

[2] UNIV AMSTERDAM,DEPT ECON STAT,1018 WB AMSTERDAM,NETHERLANDS

来源：

COMPUTATIONAL STATISTICS & DATA ANALYSIS | 1996年 / 21卷 / 05期

关键词：

components extraction; multivariate time series; nonstationarity;

D O I：

10.1016/0167-9473(95)00031-3

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

A method for modelling several observed parallel time series is proposed. The method involves seeking possible common underlying pure AR and MA components in the series. The common components are forced to be mutually uncorrelated so that univariate time series modelling and forecasting techniques can be applied. The proposed method is shown to be a useful addition to the time series analyst's toolkit, if common sources of variation in multivariate data need to be quickly identified.

引用

页码：487 / 499

页数：13

共 15 条

[1]

ANDERSON OD, 1976, TIME SERIES ANAL FOR

[2]

[Anonymous], 1994, Modern applied statistics with S-Plus

[3]

Choi B., 1992, ARMA Model Identification

[4]

Diggle P., 1990, Time series: A biostatistical introduction