Genetic algorithms for the identification of additive and innovation outliers in time series

被引：23

作者：

Baragona, R

Battaglia, F

Calzini, C

机构：

[1] Univ Rome La Sapienza, Dipartimento Sociol, I-00198 Rome, Italy

[2] Univ Rome La Sapienza, Dipartimento Stat Probabal & Stat Applicate, I-00185 Rome, Italy

来源：

COMPUTATIONAL STATISTICS & DATA ANALYSIS | 2001年 / 37卷 / 01期

关键词：

autoregressive moving average (ARMA) process; fitness function; genetic algorithms; interpolation; linear process; outliers in time series;

D O I：

10.1016/S0167-9473(00)00058-X

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

The detection of multiple outliers in time series is a cumbersome task because of the large number of combinations of the candidate locations. A genetic algorithm is proposed for the identification of additive and innovation outliers. The objective function depends on both the likelihood function and the number of outliers. Some case studies show that the algorithm is effective in detecting outliers' location and type and in estimating their size. (C) 2001 Elsevier Science B.V. All rights reserved.

引用

页码：1 / 12

页数：12

共 36 条

[1]

ABRAHAM B, 1979, BIOMETRIKA, V66, P229, DOI 10.1093/biomet/66.2.229

[2]

BARBIERI MM, 1998, STATISTICA, V58, P395

[3] Bayesian estimation of an autoregressive model using Markov chain Monte Carlo [J].