Consequences of Fitting Nonidentified Latent Class Models

Autor/inn/en	Abar, Beau; Loken, Eric
Titel	Consequences of Fitting Nonidentified Latent Class Models
Quelle	In: Structural Equation Modeling: A Multidisciplinary Journal, 19 (2012) 1, S.1-15 (15 Seiten) PDF als Volltext Verfügbarkeit
Sprache	englisch
Dokumenttyp	gedruckt; online; Zeitschriftenaufsatz
ISSN	1070-5511
DOI	10.1080/10705511.2012.634701
Schlagwörter	Probability; Statistical Bias; Multivariate Analysis; Models; Classification; Goodness of Fit + Suchen Sie Ihr Suchwort? Wahrscheinlichkeitsrechnung; Wahrscheinlichkeitstheorie; Multivariate Analyse; Analogiemodell; Classification system; Klassifikation; Klassifikationssystem
Abstract	Latent class models are becoming more popular in behavioral research. When models with a large number of latent classes relative to the number of manifest indicators are estimated, researchers must consider the possibility that the model is not identified. It is not enough to determine that the model has positive degrees of freedom. A well-known example is the latent class model with 4 binary indicators and 3 classes. This study shows that nonidentified latent class models can appear to be estimated normally when parameter estimates become fixed to a boundary of the parameter space. The consequences for the posterior probabilities of class membership given observed data are examined, along with the potential to bias predictions of distal outcomes contingent on class membership. (Contains 5 tables, 2 footnotes and 2 figures.) (As Provided).
Anmerkungen	Psychology Press. Available from: Taylor & Francis, Ltd. 325 Chestnut Street Suite 800, Philadelphia, PA 19106. Tel: 800-354-1420; Fax: 215-625-2940; Web site: http://www.tandf.co.uk/journals
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2017/4/10