Enhancing predictive power by unamalgamating multi-item scales

Trafimow, D., Hyman, M. R. and Kostyk, A. (2023) Enhancing predictive power by unamalgamating multi-item scales. Psychological Methods, (doi: 10.1037/met0000599) (PMID:37471016) (Early Online Publication)

Abstract

The generally small but touted as “statistically significant” correlation coefficients in the social sciences jeopardize theory testing and prediction. To investigate these small coefficients’ underlying causes, traditional equations such as Spearman’s (1904) classic attenuation formula, Cronbach’s (1951) alpha, and Guilford and Fruchter’s (1973) equation for the effect of additional items on a scale’s predictive power are considered. These equations’ implications differ regarding large interitem correlations enhancing or diminishing predictive power. Contrary to conventional practice, such correlations decrease predictive power when treating items as multi-item scale components but can increase predictive power when treating items separately. The implications are wide-ranging.

• Item Type: Articles
• Keywords: Correlations, Spearman, Guilford. multi-item scales, single scale items, effect size.
• Status: Early Online Publication
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Kostyk, Dr Alena
• Authors: Trafimow, D., Hyman, M. R., and Kostyk, A.
• College/School: College of Social Sciences > Adam Smith Business School > Management
• Journal Name: Psychological Methods
• Publisher: American Psychological Association
• ISSN: 1082-989X
• ISSN (Online): 1939-1463
• Published Online: 20 July 2023
• Copyright Holders: Copyright © 2023 American Psychological Association
• First Published: First published in Psychological Methods 2023
• Publisher Policy: Reproduced in accordance with the publisher copyright policy