Notice of Retraction: Outlier test and analysis method of degradation data based on linear regression

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Under the assumption that the degradation data obey the same path model form, a degradation outlier test method based on path model is presented in this paper. Through testing whether the model parameters are equal for two groups of degradation data, the abnormal data can be distinguished. The critical regions are given based on Chow test. Furthermore, a new analysis method of abnormal degradation data is proposed. It can examine the differences in model intercepts and slopes of degradation data, and determine whether the degradation abnormity is caused by the differences in intercepts or slopes or both. The presented methods are available for degradation data point and segment, and provide a scientific gist for the judgment and correction of abnormal data. Finally, an example is given to verify these methods.

Original languageEnglish
Title of host publicationQR2MSE 2013 - Proceedings of 2013 International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering
PublisherIEEE Computer Society
Pages854-858
Number of pages5
ISBN (Print)9781479910144
DOIs
StatePublished - 2013
Event2013 International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering, QR2MSE 2013 - Sichuan, China
Duration: 15 Jul 201318 Jul 2013

Publication series

NameQR2MSE 2013 - Proceedings of 2013 International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering

Conference

Conference2013 International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering, QR2MSE 2013
Country/TerritoryChina
CitySichuan
Period15/07/1318/07/13

Keywords

  • chow test
  • degradation
  • degradation path
  • linear regression
  • outlier test

Fingerprint

Dive into the research topics of 'Notice of Retraction: Outlier test and analysis method of degradation data based on linear regression'. Together they form a unique fingerprint.

Cite this