EUVIMEDEUVIMED entdecken
Open Access

A latent class pattern mixture model for nonignorable nonresponses in multivariate categorical data

Jungwun Lee, Margaret Lloyd Sieger, Jon D Phillips

Computational Statistics · 2025-11 · 40 (8) · 4367-4397

DOI: 10.1007/s00180-025-01627-0 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computational Statistics, online erschienen am 01.05.2025. Verfasst von Jungwun Lee und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biostatistics, Boston University School of Public Health, 801 Massachusetts Ave, Boston, 02118, MA, United States. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIDA NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Survey data using categorical item variables are widely used in applied research such as psychology, education, and behavioral studies. Unfortunately, survey data are highly susceptible to nonignorable missing values that may threaten the validity of statistical inference if naively ignored or inappropriately treated. This paper proposes a novel latent pattern mixture model for nonignorable missing values in multivariate categorical outcomes. The proposed model posits the existence of two categorical latent variables; one latent variable represents a nonresponse pattern, and the other represents a response pattern conditioning on the nonresponse pattern. We propose two parameter estimation strategies: the maximum-likelihood (ML) estimation using the expectation-maximization (EM) algorithm and Bayesian estimation using the Markov-Chain Monte Carlo (MCMC) algorithm. Simulation studies revealed that the ML estimation is preferred to the Bayesian estimation with noninformative priors in terms of standardized biases given the large sample size, whereas the Bayesian estimation can be preferred when the sample size is small. Finally, our real data example analyzed a data set with parental substance use disorder and revealed six latent classes of participants that are distinguished in response and missingness patterns.

Schlagwörter

Stichwörter der Autor:innen

Bayesian inferenceEM algorithmLatent class analysisMissing not at randomParental substance use disorder

Autor:innen und Institutionen

  • Department of Biostatistics, Boston University School of Public Health, 801 Massachusetts Ave, Boston, 02118, MA, United States.
  • Department of Population Health, University of Kansas School of Medicine, 3901 Rainbow Boulevard, Kansas City, 66160, State, United States.
  • University of Connecticut School of Social Work, 38 Prospect Street, Hartford, 06103, CT, United States.

Förderung

  • NIDA NIH HHS

Zitieren

APA

Lee, J., Sieger, M. L., & Phillips, J. D. (2025). A latent class pattern mixture model for nonignorable nonresponses in multivariate categorical data. Computational Statistics, 40(8), 4367-4397. https://doi.org/10.1007/s00180-025-01627-0

Vancouver

Lee J, Sieger ML, Phillips JD. A latent class pattern mixture model for nonignorable nonresponses in multivariate categorical data. Computational Statistics. 2025;40(8):4367-4397. doi:10.1007/s00180-025-01627-0

BibTeX
@article{Lee2025,
  author = {Lee, Jungwun and Sieger, Margaret Lloyd and Phillips, Jon D},
  title = {A latent class pattern mixture model for nonignorable nonresponses in multivariate categorical data},
  journal = {Computational Statistics},
  year = {2025},
  volume = {40},
  number = {8},
  pages = {4367--4397},
  doi = {10.1007/s00180-025-01627-0}
}
Kostenlos starten →