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

Influence analysis for the factor analysis model with ranking data.

Liang Xu1, Wai-Yin Poon, Sik-Yum Lee

  • 1Department of Mathematics, South-east University, Nanjing, China.

The British Journal of Mathematical and Statistical Psychology
|May 17, 2008
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

A functional promoter polymorphism of SLC2A4 is associated with aerobic endurance in a Chinese population.

European journal of sport science·2014
Same author

Near-infrared absorbing compounds based on π-extended tetrathiafulvalene open-cage fullerenes.

The Journal of organic chemistry·2014
Same author

Synthesis of oxidized glycerol monooleate-chitosan polymer and its hydrogel formation for sustained release of trimetazidine hydrochloride.

International journal of pharmaceutics·2014
Same author

Site-differentiated polyboron arenes prepared by direct C-H borylation and their highly selective Suzuki-Miyaura cross-coupling reactions.

Angewandte Chemie (International ed. in English)·2014
Same author

Artificial peptides conjugated with cholesterol and pocket-specific small molecules potently inhibit infection by laboratory-adapted and primary HIV-1 isolates and enfuvirtide-resistant HIV-1 strains.

The Journal of antimicrobial chemotherapy·2014
Same author

Aberrantly expressed lncRNAs in primary varicose great saphenous veins.

PloS one·2014
Same journal

Proficiency order invariance of MLE, MAP, EAP, and WLE in item response theory.

The British journal of mathematical and statistical psychology·2026
Same journal

Bias and precision in true-score estimation.

The British journal of mathematical and statistical psychology·2026
Same journal

Polychoric correlations under the assumption of elliptical latent traits.

The British journal of mathematical and statistical psychology·2026
Same journal

Regularized reduced rank regression for mixed predictor and response variables.

The British journal of mathematical and statistical psychology·2026
Same journal

A multiple-choice SDT model for cognitive diagnosis models.

The British journal of mathematical and statistical psychology·2026
Same journal

Modular item response and structural equation modelling via measurement and uncertainty preserving parametric modelling.

The British journal of mathematical and statistical psychology·2026
See all related articles

This study introduces a novel Monte Carlo Expectation-Maximization (MCEM) method for influence analysis in factor analysis models with ranking data. The approach simplifies identifying influential data points and assessing model sensitivity.

Area of Science:

  • Statistical Modeling
  • Data Analysis

Background:

  • Influence analysis is crucial for identifying influential observations and assessing model perturbations in statistical models.
  • Local influence methods are widely used but face challenges with factor analysis models involving ranking data due to complex likelihood calculations.
  • Existing methods struggle with the multidimensional integrals inherent in the observed data likelihood for these models.

Purpose of the Study:

  • To develop a computationally feasible influence analysis procedure for factor analysis models with ranking data.
  • To address the difficulties associated with direct application of local influence methods to these models.
  • To propose a method that efficiently identifies influential observations and assesses model sensitivity.

Main Methods:

  • Employs a Monte Carlo Expectation-Maximization (MCEM) algorithm to estimate model parameters.

Related Experiment Videos

  • Utilizes the conditional expectation of the complete data log-likelihood at the E-step of MCEM for influence measure computation.
  • Leverages by-products of the estimation procedure to minimize additional computational cost.

    • Main Results:

    • Successfully obtains maximum-likelihood estimates of model parameters using the MCEM algorithm.
    • Develops influence measures that are computationally efficient and can be derived from the estimation process.
    • Demonstrates the method's applicability through detailed discussion of various perturbation schemes and illustration with real and artificial data examples.

    Conclusions:

    • The proposed MCEM-based approach effectively overcomes the computational challenges of traditional local influence methods for factor analysis with ranking data.
    • The method provides a practical and efficient way to conduct influence analysis, aiding in robust statistical modeling.
    • This approach facilitates better understanding of data influence and model stability in complex ranking data scenarios.