Benutzer: Gast  Login
Titel:

Half-trek criterion for identifiability of latent variable models

Dokumenttyp:
Zeitschriftenaufsatz
Autor(en):
Barber, Rina Foygel; Drton, Mathias; Sturma, Nils; Weihs, Luca
Abstract:
We consider linear structural equation models with latent variables and develop a criterion to certify whether the direct causal effects between the observable variables are identifiable based on the observed covariance matrix. Linear structural equation models assume that both observed and latent variables solve a linear equation system featuring stochastic noise terms. Each model corresponds to a directed graph whose edges represent the direct effects that appear as coefficients in the equatio...     »
Stichworte:
Covariance matrix, factor analysis, Graphical model, hidden variables, latent variables, parameter identification, structural equation model
Dewey Dezimalklassifikation:
510 Mathematik
Zeitschriftentitel:
The Annals of Statistics
Jahr:
2022
Band / Volume:
50
Jahr / Monat:
2022-12
Quartal:
4. Quartal
Monat:
Dec
Heft / Issue:
6
Sprache:
en
Volltext / DOI:
doi:10.1214/22-aos2221
WWW:
PROJECTeuclid
Verlag / Institution:
Institute of Mathematical Statistics
E-ISSN:
0090-5364
Publikationsdatum:
01.12.2022
TUM Einrichtung:
Lehrstuhl für Mathematische Statistik
Format:
Text
 BibTeX