A likelihood approach to diagnostic tests in clinical medicine

This paper presents a pure likelihood approach to statistical inference and its relation to diagnostic tests in clinical medicine. The standard antagonistic frequentist approaches of Fisher and Neyman–Pearson–Wald, and the Bayesian perspective are discussed. We advocate that in medicine, usually, t...

Full description

Bibliographic Details
Main Authors: Basílio de Bragança Pereira, Carlos Alberto de Bragança Pereira
Format: Article
Language:English
Published: Instituto Nacional de Estatística | Statistics Portugal 2005-06-01
Series:Revstat Statistical Journal
Subjects:
Online Access:https://revstat.ine.pt/index.php/REVSTAT/article/view/19
_version_ 1811287015170244608
author Basílio de Bragança Pereira
Carlos Alberto de Bragança Pereira
author_facet Basílio de Bragança Pereira
Carlos Alberto de Bragança Pereira
author_sort Basílio de Bragança Pereira
collection DOAJ
description This paper presents a pure likelihood approach to statistical inference and its relation to diagnostic tests in clinical medicine. The standard antagonistic frequentist approaches of Fisher and Neyman–Pearson–Wald, and the Bayesian perspective are discussed. We advocate that in medicine, usually, the likelihood is the only source of information available. Also, it is shown that there is no difference of interpretation of the concept of likelihood in statistics and in clinical diagnostic tests. This contradicts what is usually stated.
first_indexed 2024-04-13T03:10:09Z
format Article
id doaj.art-c5ed4f68bb064b63af888e8bc1bb6f2e
institution Directory Open Access Journal
issn 1645-6726
2183-0371
language English
last_indexed 2024-04-13T03:10:09Z
publishDate 2005-06-01
publisher Instituto Nacional de Estatística | Statistics Portugal
record_format Article
series Revstat Statistical Journal
spelling doaj.art-c5ed4f68bb064b63af888e8bc1bb6f2e2022-12-22T03:05:05ZengInstituto Nacional de Estatística | Statistics PortugalRevstat Statistical Journal1645-67262183-03712005-06-013110.57805/revstat.v3i1.19A likelihood approach to diagnostic tests in clinical medicineBasílio de Bragança Pereira 0Carlos Alberto de Bragança Pereira 1Universidade Federal do Rio de Janeiro Universidade de São Paulo This paper presents a pure likelihood approach to statistical inference and its relation to diagnostic tests in clinical medicine. The standard antagonistic frequentist approaches of Fisher and Neyman–Pearson–Wald, and the Bayesian perspective are discussed. We advocate that in medicine, usually, the likelihood is the only source of information available. Also, it is shown that there is no difference of interpretation of the concept of likelihood in statistics and in clinical diagnostic tests. This contradicts what is usually stated. https://revstat.ine.pt/index.php/REVSTAT/article/view/19credibilitydiagnosabilitylikelihoodplausibilitysensitivitysignificance
spellingShingle Basílio de Bragança Pereira
Carlos Alberto de Bragança Pereira
A likelihood approach to diagnostic tests in clinical medicine
Revstat Statistical Journal
credibility
diagnosability
likelihood
plausibility
sensitivity
significance
title A likelihood approach to diagnostic tests in clinical medicine
title_full A likelihood approach to diagnostic tests in clinical medicine
title_fullStr A likelihood approach to diagnostic tests in clinical medicine
title_full_unstemmed A likelihood approach to diagnostic tests in clinical medicine
title_short A likelihood approach to diagnostic tests in clinical medicine
title_sort likelihood approach to diagnostic tests in clinical medicine
topic credibility
diagnosability
likelihood
plausibility
sensitivity
significance
url https://revstat.ine.pt/index.php/REVSTAT/article/view/19
work_keys_str_mv AT basiliodebragancapereira alikelihoodapproachtodiagnostictestsinclinicalmedicine
AT carlosalbertodebragancapereira alikelihoodapproachtodiagnostictestsinclinicalmedicine
AT basiliodebragancapereira likelihoodapproachtodiagnostictestsinclinicalmedicine
AT carlosalbertodebragancapereira likelihoodapproachtodiagnostictestsinclinicalmedicine