Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

A penalized latent class model for ordinal data.

Stacia M Desantis1, E Andrés Houseman, Brent A Coull

  • 1Department of Biostatistics, Harvard University, 655 Huntington Avenue, Boston, MA 02115, USA. sdesanti@hsph.harvard.edu

Biostatistics (Oxford, England)
|July 13, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Deciphering and Targeting the Schwannoma-Neuron-Macrophage Crosstalk for the Treatment of Schwannomatosis and Associated Pain.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

AAV hamartin gene therapy in a stochastic, cerebral mouse model of tuberous sclerosis type 1.

Molecular therapy. Methods & clinical development·2025
Same author

Increased Hemorrhage During Excision of Bevacizumab-Treated NF2-Related Vestibular Schwannomas.

The Laryngoscope·2025
Same author

Engineered AAV capsids mediate transduction of murine neurofibroma and sciatic nerve.

Gene therapy·2025
Same author

Comparative pathology boards facilitate the translation of knowledge between canine and human cancer patients.

Brain pathology (Zurich, Switzerland)·2025
Same author

A single-cell atlas of Schwannoma across genetic backgrounds and anatomic locations.

Genome medicine·2025

This study introduces a penalized latent class model for analyzing complex, high-dimensional ordinal data, improving model estimation and data interpretation for researchers. The new method enhances the analysis of challenging datasets, such as those in schwannoma studies.

Area of Science:

  • Statistics
  • Biostatistics
  • Machine Learning

Background:

  • Latent class models are valuable for data clustering but face challenges with high-dimensional, correlated ordinal data.
  • Unconstrained analyses can lead to non-estimable models, limiting the full use of ordinal variable information.

Purpose of the Study:

  • To develop a penalized latent class model for analyzing high-dimensional ordinal data.
  • To overcome estimation challenges and improve the identifiability of latent class models for such data.

Main Methods:

  • Developed a penalized latent class model incorporating stabilization of maximum likelihood estimation.
  • Applied the methodology to a dataset of schwannoma, a peripheral nerve sheath tumor, with 3 clinical subtypes and 23 ordinal histological measures.

Related Experiment Videos

Main Results:

  • The penalized model successfully stabilized estimation, allowing for the fitting of an otherwise non-identifiable ordinal latent class model.
  • Demonstrated the model's utility in a real-world application involving complex histological data.

Conclusions:

  • The penalized latent class model effectively addresses challenges in analyzing high-dimensional ordinal data.
  • This approach enhances the ability of researchers to fully exploit information from ordinal variables in complex datasets.