Detecting outliers and/or leverage points: a robust two-stage procedure with bootstrap cut-off points

<p>This paper presents a robust two-stage procedure for identification of outlying observations in regression analysis. The exploratory stage identifies leverage points and vertical outliers through a robust distance estimator based on Minimum Covariance Determinant (MCD). After deletion of th...

Full description

Saved in:
Bibliographic Details
Main Authors: Ettore Marubini, Annalisa Orenti
Format: Article
Language:English
Published: Milano University Press 2014-01-01
Series:Epidemiology, Biostatistics and Public Health
Online Access:http://ebph.it/article/view/9094
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849703576825233408
author Ettore Marubini
Annalisa Orenti
author_facet Ettore Marubini
Annalisa Orenti
author_sort Ettore Marubini
collection DOAJ
description <p>This paper presents a robust two-stage procedure for identification of outlying observations in regression analysis. The exploratory stage identifies leverage points and vertical outliers through a robust distance estimator based on Minimum Covariance Determinant (MCD). After deletion of these points, the confirmatory stage carries out an Ordinary Least Squares (OLS) analysis on the remaining subset of data and investigates the effect of adding back in the previously deleted observations. Cut-off points pertinent to different diagnostics are generated by bootstrapping and the cases are definitely labelled as good-leverage, bad-leverage, vertical outliers and typical cases. The procedure is applied to four examples.</p>
format Article
id doaj-art-184ddfab87c54014a5a2b8e447307ee2
institution DOAJ
issn 2282-0930
language English
publishDate 2014-01-01
publisher Milano University Press
record_format Article
series Epidemiology, Biostatistics and Public Health
spelling doaj-art-184ddfab87c54014a5a2b8e447307ee22025-08-20T03:17:13ZengMilano University PressEpidemiology, Biostatistics and Public Health2282-09302014-01-0111310.2427/90948984Detecting outliers and/or leverage points: a robust two-stage procedure with bootstrap cut-off pointsEttore Marubini0Annalisa Orenti1University of MilanUniversity of Milan<p>This paper presents a robust two-stage procedure for identification of outlying observations in regression analysis. The exploratory stage identifies leverage points and vertical outliers through a robust distance estimator based on Minimum Covariance Determinant (MCD). After deletion of these points, the confirmatory stage carries out an Ordinary Least Squares (OLS) analysis on the remaining subset of data and investigates the effect of adding back in the previously deleted observations. Cut-off points pertinent to different diagnostics are generated by bootstrapping and the cases are definitely labelled as good-leverage, bad-leverage, vertical outliers and typical cases. The procedure is applied to four examples.</p>http://ebph.it/article/view/9094
spellingShingle Ettore Marubini
Annalisa Orenti
Detecting outliers and/or leverage points: a robust two-stage procedure with bootstrap cut-off points
Epidemiology, Biostatistics and Public Health
title Detecting outliers and/or leverage points: a robust two-stage procedure with bootstrap cut-off points
title_full Detecting outliers and/or leverage points: a robust two-stage procedure with bootstrap cut-off points
title_fullStr Detecting outliers and/or leverage points: a robust two-stage procedure with bootstrap cut-off points
title_full_unstemmed Detecting outliers and/or leverage points: a robust two-stage procedure with bootstrap cut-off points
title_short Detecting outliers and/or leverage points: a robust two-stage procedure with bootstrap cut-off points
title_sort detecting outliers and or leverage points a robust two stage procedure with bootstrap cut off points
url http://ebph.it/article/view/9094
work_keys_str_mv AT ettoremarubini detectingoutliersandorleveragepointsarobusttwostageprocedurewithbootstrapcutoffpoints
AT annalisaorenti detectingoutliersandorleveragepointsarobusttwostageprocedurewithbootstrapcutoffpoints