Benutzer: Gast  Login
Dokumenttyp:
Zeitungsartikel 
Autor(en):
Müller, D. and Czado C. 
Titel:
Selection of Sparse Vine Copulas in High Dimensions with the Lasso 
Abstract:
We propose a novel structure selection method for high dimensional (d > 100) sparse vine copulas. Current sequential greedy approaches for structure selection require calculating spanning trees in hundreds of dimensions and fitting the pair copulas and their parameters iteratively throughout the structure selection process. Our method uses a connection between the vine and structural equation models (SEMs). The later can be estimated very fast using the Lasso, also in very high dimensions, to ob...    »
 
Stichworte:
Dependence Modeling, Vine Copula, Lasso, Sparsity 
Zeitschriftentitel:
Preprint 
Jahr:
2017 
Reviewed:
ja 
Sprache:
en 
WWW:
_blank 
Status:
Preprint / submitted 
TUM Einrichtung:
Lehrstuhl für Mathematische Statistik 
Format:
Text