Examining the Impact of Unscorable Item Responses on the Validity and Interpretability of MMPI-2/MMPI-2-RF Restructured Clinical (RC) Scale Scores

Autor/inn/en	Dragon, Wendy R.; Ben-Porath, Yossef S.; Handel, Richard W.
Titel	Examining the Impact of Unscorable Item Responses on the Validity and Interpretability of MMPI-2/MMPI-2-RF Restructured Clinical (RC) Scale Scores
Quelle	In: Assessment, 19 (2012) 1, S.101-113 (13 Seiten)Infoseite zur Zeitschrift PDF als Volltext Verfügbarkeit
Sprache	englisch
Dokumenttyp	gedruckt; online; Zeitschriftenaufsatz
ISSN	1073-1911
DOI	10.1177/1073191111415362
Schlagwörter	Personality Measures; Scores; Psychometrics; Validity; Test Interpretation; Responses; Correlation; Minnesota Multiphasic Personality Inventory + Suchen Sie Ihr Suchwort? Psychometry; Psychometrie; Gültigkeit; Test analysis; Testauswertung; Korrelation
Abstract	This article examined the impact of unscorable item responses on the psychometric validity and practical interpretability of scores on the Restructured Clinical (RC) Scales of the Minnesota Multiphasic Personality Inventory-2/Minnesota Multiphasic Personality Inventory-2-Restructured Form (MMPI-2/MMPI-2-RF). In analyses conducted with five archival samples, we found that relatively large proportions of unscorable responses (defined as 10% or more of the items scored on a scale) were relatively uncommon, occurring most often in forensic samples. Simulated unscorable responses were inserted in varying proportions (10% to 90%) in place of the responses of participants in two of the archival samples for which criterion data were available. Analyses were conducted to gauge the impact of unscorable responses on the criterion validity of scores on these scales and their interpretability. Impact on validity was evaluated by examining correlations with extra-test variables as a function of increasing levels of unscorable responding. Interpretability was evaluated by examining the proportion of participants who produced clinically elevated RC Scale scores as a function of unscorable responding. Results indicate that whereas scale score validity was relatively robust up to a level of 50% unscorable responses, interpretability was substantially compromised at only 10% unscorable responding. This suggests that prorated scores may be used to correct for the impact of unscorable responses on the interpretability of RC Scale scores at levels as high as 50% unscorable responses. Classification analyses supported this possibility. Further steps needed to explore the feasibility of using prorated scores are discussed. (Contains 13 tables and 1 note.) (As Provided).
Anmerkungen	SAGE Publications. 2455 Teller Road, Thousand Oaks, CA 91320. Tel: 800-818-7243; Tel: 805-499-9774; Fax: 800-583-2665; e-mail: journals@sagepub.com; Web site: http://sagepub.com
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2017/4/10