On the maximum likelihood estimates for the Goel-Okumoto software reliability model.
The writers demonstrate that the maximum likelihood (ML) estimates of the parameters of the Goel-Okumoto software reliability model are not consistent because the observation period for observed software failure extends to infinity. They indicate that the properties of the ML estimators as the obse...
| Publicado en: | American Statistician Vol. 55; no. 3; pp. 219 - 223 |
|---|---|
| Autores principales: | , |
| Formato: | Artículo |
| Publicado: |
American Statistical Association
August 2001
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=507701581&site=ehost-live header: @attributes: shortDbName: ssf uiTerm: 507701581 longDbName: Social Sciences Full Text (H.W. Wilson) uiTag: AN controlInfo: bkinfo: jinfo: jid: 00031305 STT jtl: American Statistician issn: 00031305 maglogo: N pubinfo: dt: August 2001 vid: 55 iid: 3 pid: 543 pub: American Statistical Association artinfo: ui: 507701581 10.1198/000313001317098211 ppf: 219 ppct: 4 formats: tig: atl: On the maximum likelihood estimates for the Goel-Okumoto software reliability model. aug: au: Jeske, Daniel R. Pham, Hoang su: Maximum likelihood statistics Computer software Reliability in engineering sug: subj: Maximum likelihood statistics Computer software Reliability in engineering ab: The writers demonstrate that the maximum likelihood (ML) estimates of the parameters of the Goel-Okumoto software reliability model are not consistent because the observation period for observed software failure extends to infinity. They indicate that the properties of the ML estimators as the observation period grows longer are especially important when the observation period matches the test interval, as extension of the test interval is the most basic way for improving the reliability of software before it is released. They observe that besides supplying insight into interpreting ML estimators in actual applications, their findings also have pedagogical value as a demonstration that asymptotic properties of ML estimators cannot be presumed. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: N holdings: @attributes: islocal: N |
|---|