Benutzer: Gast  Login
Titel:

Global identifiability of linear structural equation models

Dokumenttyp:
Zeitschriftenaufsatz
Autor(en):
Drton, Mathias; Foygel, Rina; Sullivant, Seth
Abstract:
Structural equation models are multivariate statistical models that are defined by specifying noisy functional relationships among random variables. We consider the classical case of linear relationships and additive Gaussian noise terms. We give a necessary and sufficient condition for global identifiability of the model in terms of a mixed graph encoding the linear structural equations and the correlation structure of the error terms. Global identifiability is understood to mean injectivity of...     »
Stichworte:
Covariance matrix, Gaussian distribution, graphical model, multivariate normal distribution, parameter identification, structural equation model
Dewey Dezimalklassifikation:
510 Mathematik
Zeitschriftentitel:
The Annals of Statistics
Jahr:
2011
Band / Volume:
39
Jahr / Monat:
2011-03
Quartal:
1. Quartal
Monat:
Mar
Heft / Issue:
2
Seitenangaben Beitrag:
865-886
Sprache:
en
Volltext / DOI:
doi:10.1214/10-aos859
WWW:
Project Euclid
Verlag / Institution:
Institute of Mathematical Statistics
E-ISSN:
0090-5364
Publikationsdatum:
09.03.2011
Format:
Text
 BibTeX