Benutzer: Gast  Login
Titel:

Estimating an Extreme Bayesian Network via Scalings

Dokumenttyp:
Zeitungsartikel
Autor(en):
Klüppelberg, C.; Krali, M.
Abstract:
Recursive max-linear vectors model causal dependence between its components by expressing each node variable as a max-linear function of its parental nodes in a directed acyclic graph and some exogenous innovation. Motivated by extreme value theory, innovations are assumed to have regularly varying distribution tails. We propose a scaling technique in order to determine a causal order of the node variables. All dependence parameters are then estimated from the estimated scalings. Furthermore, we...     »
Stichworte:
causal order, directed acyclic graph, extreme value statistics, graphical model, recursive max-linear model, regular variation, structural equation model, structure learning
Dewey Dezimalklassifikation:
510 Mathematik
Zeitschriftentitel:
Journal of Multivariate Analysis
Jahr:
2021
Band / Volume:
181
Jahr / Monat:
2021-01
Quartal:
1. Quartal
Monat:
Jan
Seitenangaben Beitrag:
104672
Sprache:
en
Volltext / DOI:
doi:10.1016/j.jmva.2020.104672
WWW:
arxiv.org
Verlag / Institution:
Elsevier
E-ISSN:
0047-259X
Status:
Erstveröffentlichung
Eingereicht (bei Zeitschrift):
09.12.2019
TUM Einrichtung:
Lehrstuhl für Mathematische Statistik
Format:
Text
 BibTeX