B1076
Title: Regular vine copulas with strongly chordal pattern of (conditional) independence
Authors: Dorota Kurowicka - Delft University of Technology (Netherlands) [presenting]
Abstract: Taking into account the (conditional) independence for a given data can simplify model estimation. A popular way of capturing the (conditional) independence is to use probabilistic graphical models. The relationship between strongly chordal graphs and m-saturated vines is proven. Moreover, an algorithm to construct a m-saturated vine structure corresponding to a strongly chordal graph is provided. This allows the (conditional) independence to be introduced into the regular vine copula model before its estimation. When the underlying data is sparse, the approach leads to a reduction of computational time and improves model estimation. Due to the reduction of model complexity, it is possible to evaluate all vine structures as well as to fit non-simplified vines. These advantages have been shown in the simulated and real data examples.
