Change search
ReferencesLink to record
Permanent link

Direct link
Logistic Regression: Why We Cannot Do What We Think We Can Do, and What We Can Do About It
Stockholm University, Faculty of Social Sciences, The Swedish Institute for Social Research (SOFI).
2010 (English)In: European Sociological Review, ISSN 0266-7215, E-ISSN 1468-2672, Vol. 26, no 1, 67-82 p.Article in journal (Refereed) Published
Abstract [en]

Logistic regression estimates do not behave like linear regression estimates in one important respect: They are affected by omitted variables, even when these variables are unrelated to the independent variables in the model. This fact has important implications that have gone largely unnoticed by sociologists. Importantly, we cannot straightforwardly interpret log-odds ratios or odds ratios as effect measures, because they also reflect the degree of unobserved heterogeneity in the model. In addition, we cannot compare log-odds ratios or odds ratios for similar models across groups, samples, or time points, or across models with different independent variables in a sample. This article discusses these problems and possible ways of overcoming them.

Place, publisher, year, edition, pages
2010. Vol. 26, no 1, 67-82 p.
National Category
URN: urn:nbn:se:su:diva-37017DOI: 10.1093/esr/jcp006ISI: 000274342100005OAI: diva2:291880
Available from: 2010-02-03 Created: 2010-02-03 Last updated: 2015-06-09Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Mood, Carina
By organisation
The Swedish Institute for Social Research (SOFI)
In the same journal
European Sociological Review

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 131 hits
ReferencesLink to record
Permanent link

Direct link