Unbiased Confidence Intervals for Psychological Testing: The Regression-Based True Score Approach With Scale Correction
Assessment · 2025
DOI: 10.1177/10731911251362532 ↗Kurz gefasst
Fachartikel in der Zeitschrift Assessment, 2025. Verfasst von Stefan C Schmukle. Beteiligte Einrichtung: Leipzig University, Germany. Hauptthemen laut MEDLINE: Psychological Tests. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Two different approaches for calculating confidence intervals (CIs) for individual scores in psychological testing practice have been discussed in the literature within the framework of classical test theory. The traditional approach (CI: observed score ± z · standard error of measurement) has been criticized because it does not consider the phenomenon that, with imperfect measurement, true scores will be closer to the population average than the observed scores (regression to the mean). The regression approach (CI: regression-based true score estimate ± z · standard error of the estimate) takes this effect into account, but has the disadvantage that it leads to confidence intervals that are on a different scale than the observed scores. The different scaling occurs because true scores have a smaller standard deviation than observed scores, and the extent of this shrinkage depends on the reliability of the test. Here, I suggest a scale correction for the regression-based true score estimate to preserve the original scaling. Simulations indicate that this approach has the desired properties and outperforms the two existing approaches. The regression approach with scale correction is therefore recommended for calculating confidence intervals for individual scores in psychological testing practice.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Leipzig University, Germany.
ORCID-Profile: Stefan C Schmukle
Zitieren
APA
Schmukle, S. C. (2025). Unbiased Confidence Intervals for Psychological Testing: The Regression-Based True Score Approach With Scale Correction. Assessment. https://doi.org/10.1177/10731911251362532
Vancouver
Schmukle SC. Unbiased Confidence Intervals for Psychological Testing: The Regression-Based True Score Approach With Scale Correction. Assessment. 2025. doi:10.1177/10731911251362532
BibTeX
@article{Schmukle2025,
author = {Schmukle, Stefan C},
title = {Unbiased Confidence Intervals for Psychological Testing: The Regression-Based True Score Approach With Scale Correction},
journal = {Assessment},
year = {2025},
doi = {10.1177/10731911251362532}
}
EUVIMED