EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Robust estimation of the latent trait in graded response models

Audrey Filonczuk, Ying Cheng iD

Behavior Research Methods · 14.01.2025 · 57 (1)

DOI: 10.3758/s13428-024-02574-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Behavior Research Methods, online erschienen am 14.01.2025. Verfasst von Audrey Filonczuk und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychology, University of Notre Dame, 390 Corbett Hall, Notre Dame, IN, 46556, USA. Hauptthemen laut MEDLINE: Models, Statistical, Psychometrics. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 81 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aberrant responses (e.g., careless responses, miskeyed items, etc.) often contaminate psychological assessments and surveys. Previous robust estimators for dichotomous IRT models have produced more accurate latent trait estimates with data containing response disturbances. However, for widely used Likert-type items with three or more response categories, a robust estimator for estimating latent traits does not exist. We propose a robust estimator for the graded response model (GRM) that can be applied to Likert-type items. Two weighting mechanisms for downweighting “suspicious” responses are considered: the Huber and the bisquare weight functions. Simulations reveal the estimator reduces bias for various test lengths, numbers of response categories, and types of response disturbances. The reduction in bias and stable standard errors suggests that the robust estimator for the GRM is effective in counteracting the harmful effects of response disturbances and providing more accurate scores on psychological assessments. The robust estimator is then applied to data from the Big Five Inventory-2 (Ober et al., 2021) to demonstrate its use. Potential applications and implications are discussed.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Models, StatisticalPsychometricsHumansComputer Simulation

Stichwörter der Autor:innen

Aberrant responsesGraded response model (GRM)Item response theoryRobust estimation

Autor:innen und Institutionen

  • Department of Psychology, University of Notre Dame, 390 Corbett Hall, Notre Dame, IN, 46556, USA.
  • Department of Psychology, University of Notre Dame, 390 Corbett Hall, Notre Dame, IN, 46556, USA. ycheng4@nd.edu.

ORCID-Profile: Ying Cheng

Förderung

  • National Science Foundation

Zitieren

APA

Filonczuk, A., & Cheng, Y. (2025). Robust estimation of the latent trait in graded response models. Behavior Research Methods, 57(1). https://doi.org/10.3758/s13428-024-02574-2

Vancouver

Filonczuk A, Cheng Y. Robust estimation of the latent trait in graded response models. Behavior Research Methods. 2025;57(1). doi:10.3758/s13428-024-02574-2

BibTeX
@article{Filonczuk2025,
  author = {Filonczuk, Audrey and Cheng, Ying},
  title = {Robust estimation of the latent trait in graded response models},
  journal = {Behavior Research Methods},
  year = {2025},
  volume = {57},
  number = {1},
  doi = {10.3758/s13428-024-02574-2}
}
Kostenlos starten →