SciELO - Scientific Electronic Library Online

 
vol.42 issue1Modeling Data With Semicompeting Risks: An ApModeling Data With Semicompeting Risks: An Aplication to Chronic Kidney Disease in ColombiaA Bayesian Approach to Mixed Gamma Regression Models author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Services on Demand

Article

Indicators

Related links

  • On index processCited by Google
  • Have no similar articlesSimilars in SciELO
  • On index processSimilars in Google

Share


Revista Colombiana de Estadística

Print version ISSN 0120-1751

Abstract

TOVAR CUEVAS, José Rafael; PORTILLA YELA, Jennyfer  and  ACHCAR, Jorge Alberto. A Method to Select Bivariate Copula Functions. Rev.Colomb.Estad. [online]. 2019, vol.42, n.1, pp.61-80.  Epub May 23, 2019. ISSN 0120-1751.  http://dx.doi.org/10.15446/rce.v42n1.71078.

Copula functions have been extensively used in applied statistics, becoming a good alternative for modeling the dependence of multivariate data. Each copula function has a different dependence structure. An important issue in these applications is the choice of an appropriate copula function model for each case where standard classical or Bayesian discrimination methods could be not appropriate to decide by the best copula. Considering only the special case of bivariate data, we propose a procedure obtained from a recently dependence measure introduced in the literature to select an appropriate copula for the statistical data analyses.

Keywords : Copula functions; Discrimination of copulas; Dependence measure; Ledwina measure; Selection method.

        · abstract in Spanish     · text in English     · English ( pdf )