Type I Error Inflation in the Traditional By-Participant Analysis to Metamemory Accuracy: A Generalized Mixed-Effects Model Perspective

Autor/inn/en	Murayama, Kou; Sakaki, Michiko; Yan, Veronica X.; Smith, Garry M.
Titel	Type I Error Inflation in the Traditional By-Participant Analysis to Metamemory Accuracy: A Generalized Mixed-Effects Model Perspective
Quelle	In: Journal of Experimental Psychology: Learning, Memory, and Cognition, 40 (2014) 5, S.1287-1306 (20 Seiten) PDF als Volltext Verfügbarkeit
Sprache	englisch
Dokumenttyp	gedruckt; online; Zeitschriftenaufsatz
ISSN	0278-7393
DOI	10.1037/a0036914
Schlagwörter	Metacognition; Memory; Accuracy; Statistical Analysis; Evaluation Methods; Error Patterns; Hierarchical Linear Modeling; Correlation; Perception; Bias; Inferences; Monte Carlo Methods; Simulation; Comparative Analysis; Regression (Statistics); Equations (Mathematics); Association (Psychology); Word Lists; Prediction; Cues; Visual Stimuli; English; African Languages; Recall (Psychology); Experimental Psychology + Suchen Sie Ihr Suchwort? Meta cognitive ability; Meta-cognition; Metakognitive Fähigkeit; Metakognition; Gedächtnis; Statistische Analyse; Fehlertyp; Korrelation; Wahrnehmung; Inference; Inferenz; Monte-Carlo-Methode; Simulation program; Simulationsprogramm; Regression; Regressionsanalyse; Equations; Mathematics; Gleichungslehre; Assoziation; Wortliste; Vorhersage; Stichwort; English language; Englisch; Africa; Language; Languages; Afrika; Sprachen; Afrikanische Sprache; Abberufung; Experimentelle Psychologie
Abstract	In order to examine metacognitive accuracy (i.e., the relationship between metacognitive judgment and memory performance), researchers often rely on by-participant analysis, where metacognitive accuracy (e.g., resolution, as measured by the gamma coefficient or signal detection measures) is computed for each participant and the computed values are entered into group-level statistical tests such as the "t" test. In the current work, we argue that the by-participant analysis, regardless of the accuracy measurements used, would produce a substantial inflation of Type I error rates when a random item effect is present. A mixed-effects model is proposed as a way to effectively address the issue, and our simulation studies examining Type I error rates indeed showed superior performance of mixed-effects model analysis as compared to the conventional by-participant analysis. We also present real data applications to illustrate further strengths of mixed-effects model analysis. Our findings imply that caution is needed when using the by-participant analysis, and recommend the mixed-effects model analysis. (As Provided).
Anmerkungen	American Psychological Association. Journals Department, 750 First Street NE, Washington, DC 20002. Tel: 800-374-2721; Tel: 202-336-5510; Fax: 202-336-5502; e-mail: order@apa.org; Web site: http://www.apa.org
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2020/1/01