Eigenstructure-based angle for detecting outliers in multivariate data
There are two main reasons that motivate people to detect outliers; the first is the researchers’ intention; see the example of Mr Haldum’s cases in Barnett and Lewis. The second is the effect of outliers on analyses. This article does not differentiate between the various justifications for outlier...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universiti Kebangsaan Malaysia
2014
|
| Online Access: | http://journalarticle.ukm.my/8160/ http://journalarticle.ukm.my/8160/1/21_Nazrina.pdf |
| _version_ | 1848811712173572096 |
|---|---|
| author | Nazrina Aziz, |
| author_facet | Nazrina Aziz, |
| author_sort | Nazrina Aziz, |
| building | UKM Institutional Repository |
| collection | Online Access |
| description | There are two main reasons that motivate people to detect outliers; the first is the researchers’ intention; see the example of Mr Haldum’s cases in Barnett and Lewis. The second is the effect of outliers on analyses. This article does not differentiate between the various justifications for outlier detection. The aim was to advise the analyst about observations that are isolated from the other observations in the data set. In this article, we introduce the eigenstructure based angle for outlier detection. This method is simple and effective in dealing with masking and swamping problems. The method proposed is illustrated and compared with Mahalanobis distance by using several data sets. |
| first_indexed | 2025-11-14T23:50:45Z |
| format | Article |
| id | oai:generic.eprints.org:8160 |
| institution | Universiti Kebangasaan Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T23:50:45Z |
| publishDate | 2014 |
| publisher | Universiti Kebangsaan Malaysia |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | oai:generic.eprints.org:81602016-12-14T06:46:24Z http://journalarticle.ukm.my/8160/ Eigenstructure-based angle for detecting outliers in multivariate data Nazrina Aziz, There are two main reasons that motivate people to detect outliers; the first is the researchers’ intention; see the example of Mr Haldum’s cases in Barnett and Lewis. The second is the effect of outliers on analyses. This article does not differentiate between the various justifications for outlier detection. The aim was to advise the analyst about observations that are isolated from the other observations in the data set. In this article, we introduce the eigenstructure based angle for outlier detection. This method is simple and effective in dealing with masking and swamping problems. The method proposed is illustrated and compared with Mahalanobis distance by using several data sets. Universiti Kebangsaan Malaysia 2014-12 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/8160/1/21_Nazrina.pdf Nazrina Aziz, (2014) Eigenstructure-based angle for detecting outliers in multivariate data. Sains Malaysiana, 43 (12). pp. 1973-1977. ISSN 0126-6039 http://www.ukm.my/jsm/ |
| spellingShingle | Nazrina Aziz, Eigenstructure-based angle for detecting outliers in multivariate data |
| title | Eigenstructure-based angle for detecting outliers in multivariate data |
| title_full | Eigenstructure-based angle for detecting outliers in multivariate data |
| title_fullStr | Eigenstructure-based angle for detecting outliers in multivariate data |
| title_full_unstemmed | Eigenstructure-based angle for detecting outliers in multivariate data |
| title_short | Eigenstructure-based angle for detecting outliers in multivariate data |
| title_sort | eigenstructure-based angle for detecting outliers in multivariate data |
| url | http://journalarticle.ukm.my/8160/ http://journalarticle.ukm.my/8160/ http://journalarticle.ukm.my/8160/1/21_Nazrina.pdf |