Benutzer: Gast  Login
Titel:

Testing many constraints in possibly irregular models using incomplete U-statistics

Dokumenttyp:
Zeitschriftenaufsatz
Autor(en):
Sturma, Nils; Drton, Mathias; Leung, Dennis
Abstract:
We consider the problem of testing a null hypothesis defined by equality and inequality constraints on a statistical parameter. Testing such hypotheses can be challenging because the number of relevant constraints may be on the same order or even larger than the number of observed samples. Moreover, standard distributional approximations may be invalid due to irregularities in the null hypothesis. We propose a general testing methodology that aims to circumvent these difficulties. The constraint...     »
Stichworte:
Gaussian approximation, high dimensions, incomplete U-statistics, latent-tree model, multiplier bootstrap, non-asymptotic bound
Dewey Dezimalklassifikation:
510 Mathematik
Zeitschriftentitel:
Journal of the Royal Statistical Society Series B: Statistical Methodology
Jahr:
2024
Jahr / Monat:
2024-03
Quartal:
1. Quartal
Monat:
Mar
Seitenangaben Beitrag:
1--26
Sprache:
en
Volltext / DOI:
doi:10.1093/jrsssb/qkae022
WWW:
Journal of the Royal Statistical Society Series B: Statistical Methodology
Verlag / Institution:
Oxford University Press (OUP)
Verlagsort:
Oxford, UK
Print-ISSN:
1369-7412
E-ISSN:
1467-9868
Publikationsdatum:
07.03.2024
Semester:
WS 23-24
TUM Einrichtung:
Lehrstuhl für Mathematische Statistik
Format:
Text
 BibTeX