Robust Estimation of Polychoric Correlation
Psychometrika · 2026-03 · 91 (1) · 247-278
DOI: 10.1017/psy.2025.10066 ↗Kurz gefasst
Fachartikel in der Zeitschrift Psychometrika, online erschienen am 01.12.2025. Verfasst von Max Welz und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychology, https://ror.org/02crff812University of Zurich, Switzerland. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Sociale en Geesteswetenschappen, NWO.
Abstract (Originalsprache)
Polychoric correlation is often an important building block in the analysis of rating data, particularly for structural equation models. However, the commonly employed maximum likelihood (ML) estimator is highly susceptible to misspecification of the polychoric correlation model, for instance, through violations of latent normality assumptions. We propose a novel estimator that is designed to be robust against partial misspecification of the polychoric model, that is, when the model is misspecified for an unknown fraction of observations, such as careless respondents. To this end, the estimator minimizes a robust loss function based on the divergence between observed frequencies and theoretical frequencies implied by the polychoric model. In contrast to existing literature, our estimator makes no assumption on the type or degree of model misspecification. It furthermore generalizes ML estimation, is consistent as well as asymptotically normally distributed, and comes at no additional computational cost. We demonstrate the robustness and practical usefulness of our estimator in simulation studies and an empirical application on a Big Five administration. In the latter, the polychoric correlation estimates of our estimator and ML differ substantially, which, after further inspection, is likely due to the presence of careless respondents that the estimator helps identify.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Psychology, https://ror.org/02crff812University of Zurich, Switzerland.
- Department of Econometrics, https://ror.org/057w15z03Erasmus University Rotterdam, The Netherlands.
- Department of Psychology, https://ror.org/03vek6s52Harvard University, USA.
ORCID-Profile: Max Welz, Andreas Alfons
Förderung
- Sociale en Geesteswetenschappen, NWO
Zitieren
APA
Welz, M., Mair, P., & Alfons, A. (2026). Robust Estimation of Polychoric Correlation. Psychometrika, 91(1), 247-278. https://doi.org/10.1017/psy.2025.10066
Vancouver
Welz M, Mair P, Alfons A. Robust Estimation of Polychoric Correlation. Psychometrika. 2026;91(1):247-278. doi:10.1017/psy.2025.10066
BibTeX
@article{Welz2026,
author = {Welz, Max and Mair, Patrick and Alfons, Andreas},
title = {Robust Estimation of Polychoric Correlation},
journal = {Psychometrika},
year = {2026},
volume = {91},
number = {1},
pages = {247--278},
doi = {10.1017/psy.2025.10066}
}
EUVIMED