Benutzer: Gast  Login
Titel:

Selection of Sparse Vine Copulas in High Dimensions with the Lasso

Dokumenttyp:
Zeitungsartikel
Autor(en):
Müller, D. and Czado C.
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
Dewey Dezimalklassifikation:
510 Mathematik
Zeitschriftentitel:
Statistics and Computing
Jahr:
2019
Band / Volume:
29
Jahr / Monat:
2019-03
Quartal:
1. Quartal
Monat:
Mar
Heft / Issue:
2
Seitenangaben Beitrag:
269-287
Reviewed:
ja
Sprache:
en
Volltext / DOI:
doi:10.1007/s11222-018-9807-5
Verlag / Institution:
Springer US
Verlagsort:
New York, NY
Print-ISSN:
0960-3174
E-ISSN:
1573-1375
Status:
Erstveröffentlichung
Publikationsdatum:
15.03.2019
TUM Einrichtung:
Professur für Angewandte Mathematische Statistik
Format:
Text
 BibTeX