File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Scopus: eid_2-s2.0-12644316894
- WOS: WOS:A1995TC68500008
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Detecting influential observations for estimated probabilities in multiple discriminant analysis
Title | Detecting influential observations for estimated probabilities in multiple discriminant analysis |
---|---|
Authors | |
Keywords | Estimated Probabilities Influence Measures Multiple Discriminant Analysis Omission Approach |
Issue Date | 1995 |
Publisher | Elsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/csda |
Citation | Computational Statistics and Data Analysis, 1995, v. 20 n. 5, p. 557-568 How to Cite? |
Abstract | The estimated probability that an observation of unknown source belongs to a certain population is often of interest in multiple discriminant analysis. Four diagnostic measures defined on this probability are proposed. Various extensions on the measures have been made. The performance of the measures for detecting influential observations is studied using a small simulation study and a real data set. The results seem satisfactory. © 1995. |
Persistent Identifier | http://hdl.handle.net/10722/172410 |
ISSN | 2023 Impact Factor: 1.5 2023 SCImago Journal Rankings: 1.008 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Fung, WK | en_US |
dc.date.accessioned | 2012-10-30T06:22:23Z | - |
dc.date.available | 2012-10-30T06:22:23Z | - |
dc.date.issued | 1995 | en_US |
dc.identifier.citation | Computational Statistics and Data Analysis, 1995, v. 20 n. 5, p. 557-568 | en_US |
dc.identifier.issn | 0167-9473 | en_US |
dc.identifier.uri | http://hdl.handle.net/10722/172410 | - |
dc.description.abstract | The estimated probability that an observation of unknown source belongs to a certain population is often of interest in multiple discriminant analysis. Four diagnostic measures defined on this probability are proposed. Various extensions on the measures have been made. The performance of the measures for detecting influential observations is studied using a small simulation study and a real data set. The results seem satisfactory. © 1995. | en_US |
dc.language | eng | en_US |
dc.publisher | Elsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/csda | en_US |
dc.relation.ispartof | Computational Statistics and Data Analysis | en_US |
dc.rights | Computational Statistics and Data Analysis. Copyright © Elsevier BV. | - |
dc.subject | Estimated Probabilities | en_US |
dc.subject | Influence Measures | en_US |
dc.subject | Multiple Discriminant Analysis | en_US |
dc.subject | Omission Approach | en_US |
dc.title | Detecting influential observations for estimated probabilities in multiple discriminant analysis | en_US |
dc.type | Article | en_US |
dc.identifier.email | Fung, WK: wingfung@hku.hk | en_US |
dc.identifier.authority | Fung, WK=rp00696 | en_US |
dc.description.nature | link_to_subscribed_fulltext | en_US |
dc.identifier.scopus | eid_2-s2.0-12644316894 | en_US |
dc.identifier.hkuros | 11576 | - |
dc.identifier.volume | 20 | en_US |
dc.identifier.issue | 5 | en_US |
dc.identifier.spage | 557 | en_US |
dc.identifier.epage | 568 | en_US |
dc.identifier.isi | WOS:A1995TC68500008 | - |
dc.publisher.place | Netherlands | en_US |
dc.identifier.scopusauthorid | Fung, WK=13310399400 | en_US |
dc.identifier.issnl | 0167-9473 | - |