Change search
ReferencesLink to record
Permanent link

Direct link
A Method to Maximize the Information of a Continuous Variable in Relation to a Dichotomous Grouping Variable: Cutpoint Analysis
Károli Gáspár University of the Reformed Church in Budapest, Ungern.
Stockholm University, Faculty of Social Sciences, Department of Psychology.
2012 (English)In: Hungarian Statistical Review, ISSN 0039-0690, Vol. 90, no Special number 16, 101-122 p.Article in journal (Refereed) Published
Abstract [en]

In statistical analyses the researcher should normally use all the relevant information in the data. This argument has been used to advise against the habit of dichotomizing (approximately) continuous variables. However, if, for instance, a continuous variable is not normally distributed, it is possible that an optimal dichotomization can reveal relationships between variables otherwise obscured. Two analytical situations when this might apply were treated: 1. The study of the relationship between an independent dichotomous grouping variable and a dependent continuous variable and 2. the discrimination between two groups by identifying an optimal cutpoint in one or more continuous ariables, treated as the predictor(s). For these purposes, cutpoint analysis (CPA) is introduced as a method for finding an optimal categorization of a continuous variable together with a computer package (ROPstat) to carry out the analysis. Three empirical examples are given that show the usefulness of CPA as compared to conventional analyses.

Place, publisher, year, edition, pages
Budapest: Hungarian central statistical office , 2012. Vol. 90, no Special number 16, 101-122 p.
Keyword [en]
group comparison, best discriminating point, detailed comparison of distribution, dichotomization, cutpoint analysis, relationship
National Category
Research subject
URN: urn:nbn:se:su:diva-86179OAI: diva2:586384
Available from: 2013-01-11 Created: 2013-01-11 Last updated: 2013-03-11

Open Access in DiVA

Fulltext(269 kB)81 downloads
File information
File name FULLTEXT01.pdfFile size 269 kBChecksum SHA-512
Type fulltextMimetype application/pdf

Other links

Fulltext, med 6 månaders eftersläpning

Search in DiVA

By author/editor
Bergman, Lars R.
By organisation
Department of Psychology

Search outside of DiVA

GoogleGoogle Scholar
Total: 81 downloads
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

Total: 219 hits
ReferencesLink to record
Permanent link

Direct link