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

Latent transition analysis: inference and estimation.

Hwan Chung1, Stephanie T Lanza, Eric Loken

  • 1Department of Epidemiology, Michigan State University, East Lansing, MI 48824, U.S.A. hchung@epi.msu.edu

Statistics in Medicine
|December 12, 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

Author's response to: "The need to advance the measurement of exposure to digital content."

Nicotine & tobacco research : official journal of the Society for Research on Nicotine and Tobacco·2026
Same author

Daily motivation for and perceived accessibility of nondrug reward among people in long-term recovery from opioid use disorder.

Drug and alcohol dependence·2026
Same author

Unveiling topic dependencies through a multilevel topic model: a hierarchical approach to enhanced interpretability.

Journal of applied statistics·2026
Same author

Between- and within-person predictors of missingness in intensive longitudinal data among people in outpatient treatment for opioid use disorder.

Psychological assessment·2026
Same author

Heterogeneity of Within-Day Simultaneous Alcohol and Cannabis Use Behaviors Among Young Adults: A Multilevel Latent Class Analysis.

Journal of studies on alcohol and drugs·2026
Same author

Patterns of ENDS-Related Content Exposure on Social Media Among US Adolescents and Young Adults.

Nicotine & tobacco research : official journal of the Society for Research on Nicotine and Tobacco·2025
Same journal

A Mixture of Distributed Lag Non-Linear Models to Account for Spatially Heterogeneous Exposure-Lag-Response Associations.

Statistics in medicine·2026
Same journal

Practical Considerations for Gaussian Process Modeling for Causal Inference in Quasi-Experimental Studies With Panel Data.

Statistics in medicine·2026
Same journal

Covariate Adjustment for Wilcoxon Two Sample Statistic and Test.

Statistics in medicine·2026
Same journal

Beyond Fixed Thresholds: Optimizing Summaries of Wearable Device Data via Piecewise Linearization of Quantile Functions.

Statistics in medicine·2026
Same journal

A Causal Framework for Evaluating the Total Effect of Strategies Aiming to Expand Screening and to Improve Outcomes.

Statistics in medicine·2026
Same journal

Causal Effects on Nonterminal Event Time With Application to Antibiotic Usage and Future Resistance.

Statistics in medicine·2026
See all related articles

Latent transition analysis (LTA) estimation can be challenging with small samples. This study introduces a dynamic data-dependent prior to improve maximum likelihood and Bayesian inference for LTA in such cases.

Area of Science:

  • Statistics
  • Quantitative Psychology
  • Computational Social Science

Background:

  • Latent transition analysis (LTA) is a statistical method for analyzing changes in categorical latent variables over time.
  • Maximum likelihood (ML) and Bayesian methods (using Markov chain Monte Carlo, MCMC) are common for estimating LTA parameters.
  • Estimation challenges arise in LTA, particularly with small sample sizes, due to potential difficulties in likelihood function behavior.

Purpose of the Study:

  • To investigate problems encountered in latent transition analysis (LTA) inference with small samples.
  • To propose and evaluate a novel dynamic data-dependent prior for LTA when dealing with limited data.
  • To compare the performance of conventional estimation methods against those incorporating the proposed prior.

Main Methods:

Related Experiment Videos

  • Exploration of estimation difficulties using a simulation study.
  • Application to a real-world substance use dataset.
  • Development and implementation of a dynamic data-dependent prior for LTA.

Main Results:

  • Conventional maximum likelihood (ML) and Bayesian estimates can be erratic with small sample sizes in LTA.
  • The proposed dynamic data-dependent prior demonstrates potential to alleviate estimation problems in small samples.
  • Comparative analysis shows improved inference stability when using the prior with limited data.

Conclusions:

  • Small sample sizes pose significant challenges for standard latent transition analysis (LTA) estimation.
  • Incorporating a dynamic data-dependent prior can enhance the reliability of LTA, especially with limited data.
  • The proposed prior offers a practical solution for improving LTA inference in data-scarce situations.