A comparison of several procedures for identifying outliers in contaminated ARMA processes

MaRDI QIDQ1966014zbMATH OpenFDO

Authors Thomas Flak, R. Sigmund, Wolfgang Schmid

Publication date 2 March 2000

Published in Computational Statistics (Search for Journal in Brave)

zbMATH Keywords

ARMA modelsidentificationoutlierssimulation study

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10)

Review text

A systematic comparison of several procedures for identifying outliers in contaminated ARMA processes is given. Performance criteria for the identification method are discussed. Results of simulations for AR(1) processes under various outlier configurations are given. The use of outlier identification procedures is discussed in the appendix.

Recommendations

• Determining the order of an arm a model from outlier contaminated data
• AN OUTLIER TEST FOR TIME SERIES BASED ON A TWO-SIDED PREDICTOR
• The Identification of Multiple Outliers in ARIMA Models
• Outliers in a multivariate autoregressive moving-average process
• The Multiple Outlier Problem in Time Series Analysis

Cited in

(5)

• Out of control (outlier) detection in business data using the \(\mathrm{ARMA}(1,1)\) model
• Time series analysis of process data
• Determining the order of an arm a model from outlier contaminated data
• The Identification of Multiple Outliers in ARIMA Models
• Selecting sub-set autoregressions from outlier contaminated data.

This page was built for publication: A comparison of several procedures for identifying outliers in contaminated ARMA processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1966014)