The Effects of Using Partial or Uncorrected Correlation Matrices When Comparing Network and Latent Variable Models

Autor/in	McFarland, Dennis
Titel	The Effects of Using Partial or Uncorrected Correlation Matrices When Comparing Network and Latent Variable Models
Quelle	In: Journal of Intelligence, 8 (2020), Artikel 7 (6 Seiten) PDF als Volltext kostenfreie Datei Verfügbarkeit
Zusatzinformation	ORCID (McFarland, Dennis)
Dokumenttyp	gedruckt; online; Zeitschriftenaufsatz
ISSN	2079-3200
Schlagwörter	Correlation; Matrices; Adults; Intelligence Tests; Networks; Network Analysis; Models; Scores; Psychometrics; Cognitive Processes; Wechsler Adult Intelligence Scale + Suchen Sie Ihr Suchwort? Korrelation; Matrizenrechnung; Intelligence test; Intelligenztest; Netzplantechnik; Analogiemodell; Psychometry; Psychometrie; Cognitive process; Kognitiver Prozess
Abstract	Network models of the WAIS-IV based on regularized partial correlation matrices have been reported to outperform latent variable models based on uncorrected correlation matrices. The present study sought to compare network and latent variable models using both partial and uncorrected correlation matrices with both types of models. The results show that a network model provided better fit to matrices of partial correlations but latent variable models provided better fit to matrices of full correlations. This result is due to the fact that the use of partial correlations removes most of the covariance common to WAIS-IV tests. Modeling should be based on uncorrected correlations since these represent the majority of shared variance between WAIS-IV test scores. (As Provided).
Anmerkungen	MDPI AG. Klybeckstrasse 64, 4057 Basel, Switzerland. e-mail: indexing@mdpi.com; e-mail: jintelligence@mdpi.com; Web site: https://www.mdpi.com/journal/jintelligence
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2024/1/01