Copula based modelling of non-exchangeable random vector distributions and its applicationsSupervisor: prof. RNDr. Radko Mesiar, DrSc.
This page shows details on the project. The primary projects are displayed together with a list of sub-projects.
|Project description:||The enormous potential of the copula theory applications when modeling the stochastic dependence structure of random vectors is limited of the buffer of known copula classes and by appropriate fitting methods. The majority of known copula classes contains bivariate symmetric copulas, where the permutation of the random variables order has no influence into the resulting dependence structure. Consequently, the fitting methods deal and are applicable mostly to symmetric bivariate either based on the given theoretical properties or based on practical requirements. Very promissing is the class of Archimax copulas, where the 3-or more-dimensional generalization is still a challenger. Subsequently, we plan to develop software tools for fitting copulas to real data based on Mathematical system and in R-CRANE framework. Obtained results will be appied to the modeling of hydrological events. Project will be realized in cooperation with JKU Linz, Austria, University Lecce, Italy and University Ghent, Belgium.|
|Kind of project:||APVV - Program LPP ()|
|Department:||Department of Mathematics and Constructive Geometry (FCE)|
|Project identification:||LPP - 0004-07|
|Project status:||Successfully completed|
|Project start date :||01. 07. 2008|
|Project close date:||30. 06. 2011|
|Number of workers in the project:||2|
|Number of official workers in the project:||0|