EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Regularized Joint Maximum Likelihood Estimation for Exploratory Multidimensional Item Response Theory Models

Pengyuan Travis Yang iD, Wilco Emons iD, Katrijn Van Deun

Psychometrika · 07.07.2026 · 1-29

DOI: 10.1017/psy.2026.10132 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Psychometrika, online erschienen am 07.07.2026. Verfasst von Pengyuan Travis Yang und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Exploratory multidimensional item response theory (MIRT), also known as exploratory item factor analysis, presents substantial computational and statistical challenges in large-scale applications, particularly when the latent space is high-dimensional (HiMIRT). Building on a previously proposed joint maximum likelihood estimation framework, this article presents two advanced regularized MIRT methods: lasso HiMIRT and card HiMIRT . Both methods leverage the minimization–majorization algorithm to transform the likelihood problem into a least squares problem. lasso HiMIRT incorporates an ℓ 1 $\ell _1$ script l 1 penalty within an alternating optimization–alternating direction method of multipliers framework to achieve sparse loading matrix estimation. In contrast, card HiMIRT imposes cardinality constraints to control the number of nonzero loadings in the model. Simulation studies show that both proposed methods accurately recover the true sparse structure of the loading matrix, effectively distinguishing between zero and nonzero elements. In addition to their precision, both approaches demonstrate strong computational efficiency. The proposed alternating optimization framework is also straightforward to implement and extend. The complementary strengths of the two approaches may benefit the practical applications of MIRT analysis. An empirical example based on data from the revised version of Eysenck’s Personality Questionnaire further illustrates their practical applicability.

Autor:innen und Institutionen

ORCID-Profile: Pengyuan Travis Yang, Wilco Emons

Zitieren

APA

Yang, P. T., Emons, W., & Van Deun, K. (2026). Regularized Joint Maximum Likelihood Estimation for Exploratory Multidimensional Item Response Theory Models. Psychometrika, 1-29. https://doi.org/10.1017/psy.2026.10132

Vancouver

Yang PT, Emons W, Van Deun K. Regularized Joint Maximum Likelihood Estimation for Exploratory Multidimensional Item Response Theory Models. Psychometrika. 2026:1-29. doi:10.1017/psy.2026.10132

BibTeX
@article{Yang2026,
  author = {Yang, Pengyuan Travis and Emons, Wilco and Van Deun, Katrijn},
  title = {Regularized Joint Maximum Likelihood Estimation for Exploratory Multidimensional Item Response Theory Models},
  journal = {Psychometrika},
  year = {2026},
  pages = {1--29},
  doi = {10.1017/psy.2026.10132}
}
Kostenlos starten →