Noncollapsibility, confounding, and sparse-data bias. Part 2: What should researchers make of persistent controversies about the odds ratio?
Causality
Collapsibility
Confounding
Logistic regression
Noncollapsibility
Odds Ratio
Rate Ratio
Simpson's paradox
Sparse-data bias
Journal
Journal of clinical epidemiology
ISSN: 1878-5921
Titre abrégé: J Clin Epidemiol
Pays: United States
ID NLM: 8801383
Informations de publication
Date de publication:
11 2021
11 2021
Historique:
received:
14
03
2021
revised:
04
06
2021
accepted:
04
06
2021
pubmed:
14
6
2021
medline:
21
12
2021
entrez:
13
6
2021
Statut:
ppublish
Résumé
A previous note illustrated how the odds of an outcome have an undesirable property for risk summarization and communication: Noncollapsibility, defined as a failure of a group measure to represent a simple average of the measure over individuals or subgroups. The present sequel discusses how odds ratios amplify odds noncollapsibility and provides a basic numeric illustration of how noncollapsibility differs from confounding of effects (with which it is often confused). It also draws a connection of noncollapsibility to sparse-data bias in logistic, log-linear, and proportional-hazards regression.
Identifiants
pubmed: 34119647
pii: S0895-4356(21)00182-7
doi: 10.1016/j.jclinepi.2021.06.004
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
264-268Informations de copyright
Copyright © 2021 Elsevier Inc. All rights reserved.