Dissimilarities between categorical variables
Rodrigo Andrés Peñaloza ()
No 351, Working papers - Textos para Discussao do Departamento de Economia da Universidade de Brasilia from Departamento de Economia da Universidade de Brasilia
When we deal with two categorical variables, Ginis index of distributional transvariation is a most usefull tool to measure the distributional difference between them. By means of a modi ed transvariation, which we call Euclidean transvari- ation, we showed that our measure of transvariation can be decomposed into the difference of two terms: a measure of categorical separation and the average variabil- ity. This decomposition allows us to view the dissimilarities between two categorical variables through three di¤erent lenses: distribution, modality, and variability. Fi- nally, by de ning a simpler measure of statistical dependence based on Pearsons X2, we prove a relationship between statistical dependence and the transvariational impact of one variable onto another.
Keywords: nominal variables; transvariation; degree of dependence (search for similar items in EconPapers)
JEL-codes: C49 (search for similar items in EconPapers)
New Economics Papers: this item is included in nep-ecm
References: Add references at CitEc
Citations Track citations by RSS feed
Downloads: (external link)
http://vsites.unb.br/face/eco/textos/didaticos/WP%20351.pdf First version, 2011 (application/pdf)
Our link check indicates that this URL is bad, the error code is: 500 Can't connect to vsites.unb.br:80
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
Persistent link: http://EconPapers.repec.org/RePEc:brs:wpaper:351
Access Statistics for this paper
More papers in Working papers - Textos para Discussao do Departamento de Economia da Universidade de Brasilia from Departamento de Economia da Universidade de Brasilia Universidade de Brasília UnB - Campus Universitário Darcy Ribeiro Asa Norte CEP 70910-900, Brasília, Brasil. Contact information at EDIRC.
Series data maintained by Luciano Póvoa ().