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

Testing Thurstonian Case V ranking models using posterior predictive checks.

R C Tsai1, G Yao

  • 1Department of Psychology, University of Illinois at Urbana-Champaign 61820, USA.

The British Journal of Mathematical and Statistical Psychology
|December 8, 2000
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

Research on quantitative assessment of renal tubular function based on renal dynamic imaging.

Revista espanola de medicina nuclear e imagen molecular·2025
Same author

Comparative genomics and untargeted metabolomics analysis of dairy-derived Lacticaseibacillus rhamnosus strains and their potential applications in dairy fermentation.

Journal of dairy science·2025
Same author

Invasive fungal infection is associated with antibiotic exposure in preterm infants: a multi-centre prospective case-control study.

The Journal of hospital infection·2023
Same author

[Cytotoxic effect of photodynamic liposome gel combined with trastuzumab on drugresistant breast cancer cells <i>in vitro</i>].

Nan fang yi ke da xue xue bao = Journal of Southern Medical University·2021
Same author

Potential role of lnc-PTGS2 in fibrosis progression after laminectomy via targeting EGR1.

Journal of biological regulators and homeostatic agents·2020
Same author

3,4-Methylenedioxymethamphetamine causes retinal damage in C57BL/6J mice.

Human & experimental toxicology·2020

Posterior predictive checks (PPC) effectively validate Thurstonian Case V ranking models, even with sparse data. This Monte Carlo study shows PPC detects model misfits better than traditional tests.

Area of Science:

  • Psychometrics
  • Statistical Modeling
  • Computational Statistics

Background:

  • Standard goodness-of-fit tests have limitations for Thurstonian Case V ranking models, especially with small sample sizes.
  • Posterior predictive checks (PPC) offer a potential alternative for assessing model fit in psychometric analyses.
  • Thurstonian models are widely used for analyzing ranking data, but their assumptions require careful validation.

Purpose of the Study:

  • To investigate the validity and utility of posterior predictive checks (PPC) for Thurstonian Case V ranking models.
  • To compare the performance of PPC against standard goodness-of-fit tests in detecting model misfits.
  • To evaluate PPC's effectiveness under conditions violating Case V assumptions, including heterogeneous variances and mixed populations.

Main Methods:

Related Experiment Videos

  • A Monte Carlo simulation study was conducted to generate ranking data under various conditions.
  • Posterior predictive checks (PPC) were implemented using several test quantities to assess model fit.
  • The study examined model fit for different sample sizes and simulated violations of Thurstonian Case V assumptions.

Main Results:

  • Posterior predictive checks (PPC) demonstrated significant utility in detecting both local and global misfits of the Thurstonian Case V model.
  • The effectiveness of PPC was evident even when ranking data were sparse or assumptions of the Case V model were violated.
  • PPC proved more informative than traditional goodness-of-fit tests, particularly in scenarios with limited data or assumption violations.

Conclusions:

  • Posterior predictive checks (PPC) are a valuable and robust method for testing the fit of Thurstonian Case V ranking models.
  • The PPC method provides reliable assessments of model fit, even in challenging data situations like sparsity or violated assumptions.
  • Researchers can confidently employ PPC as an alternative or supplement to standard tests for validating Thurstonian ranking models.