Your new experience awaits. Try the new design now and help us make it even better

ORIGINAL RESEARCH article

Front. Psychol.

Sec. Quantitative Psychology and Measurement

Volume 16 - 2025 | doi: 10.3389/fpsyg.2025.1652403

This article is part of the Research TopicStatistical Guidelines: New Developments in Statistical Methods and Psychometric Tools – Volume IIView all articles

Comparing the ability of the IAT and of the SC-IAT to account for behavioral outcomes: A Re-analysis Using Linear Mixed-Effects Models

Provisionally accepted
  • 1Department of Psychology and Cognitive Science, University of Trento, Rovereto, Italy
  • 2Universita degli Studi di Padova, Padua, Italy

The final, formatted version of the article will be published soon.

Implicit measures are widely used to indirectly assess psychological constructs and predict behavior. Nonetheless, comparisons of their predictive validity often suffer from methodological limitations, including administration inconsistencies, scoring differences, and unaccounted sources of variability related to data structure and experimental design. To overcome the administration and scoring differences, Epifania et al. (2020a) compared the predictive power of the Implicit Association Test (IAT) and its single-category variant (SC-IAT) by introducing new scoring methods. However, the authors did not adequately control for the fully-crossed nature of the data or the within-subjects design. This study re-analyzes the data from Epifania et al. (2020a) with a modeling framework that integrates a Rasch-like parameterization of accuracies and response times while accounting for the sources of variability related to the fully-crossed nature of the data and the within-subject design. Results of the re-analyses partially align with the ones in the original study and further corroborate the higher predictive validity of the IAT. However, the modeling approach allowed for unveiling the contribution of one of the SC-IATs to the choice prediction, which was probably lost with the typical scoring because of the error variance related to their computation.

Keywords: Rasch model, Log-normal model, Implicit Association Test, Single category implicit association test, Re-analyses

Received: 23 Jun 2025; Accepted: 30 Sep 2025.

Copyright: © 2025 Epifania, Anselmi and Robusto. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence:
Ottavia M. Epifania, ottavia.epifania@unitn.it
Pasquale Anselmi, pasquale.anselmi@unipd.it

Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.