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

Mixture models for eye-tracking data: a case study

D K Pauler1, M D Escobar, J A Sweeney

  • 1Department of Statistics, Carnegie Mellon University, Pittsburgh, PA 15213, USA.

Statistics in Medicine
|July 15, 1996
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

Risk scoring for time to end-stage knee osteoarthritis: data from the Osteoarthritis Initiative.

Osteoarthritis and cartilage·2020
Same author

Genome-wide association studies of smooth pursuit and antisaccade eye movements in psychotic disorders: findings from the B-SNIP study.

Translational psychiatry·2017
Same author

Deviation from expected cognitive ability across psychotic disorders.

Schizophrenia research·2017
Same author

Alterations in the functional neural circuitry supporting flexible choice behavior in autism spectrum disorders.

Translational psychiatry·2016
Same author

5HT<sub>2A</sub> receptor blockade in dorsomedial striatum reduces repetitive behaviors in BTBR mice.

Genes, brain, and behavior·2016
Same author

Reduced habituation of auditory evoked potentials indicate cortical hyper-excitability in Fragile X Syndrome.

Translational psychiatry·2016

Finite mixture models may overestimate subgroups in biomedical data. Continuous mixture models offer a viable alternative, especially for small sample sizes, preventing spurious findings in analyses like schizophrenia eye-tracking studies.

Area of Science:

  • Biostatistics
  • Psychiatric Epidemiology
  • Computational Neuroscience

Background:

  • Biomedical data often exhibits heterogeneity, necessitating advanced statistical modeling.
  • Finite mixture models (FMMs) capture discrete subgroups, while continuous mixture models (CMMs) address over-dispersion.
  • Overfitting in FMMs can lead to misinterpretation of spurious subgroups, particularly with limited data.

Purpose of the Study:

  • To propose CMMs as a robust alternative to FMMs when dealing with potential lack of model fit.
  • To evaluate the utility of CMMs in modeling heterogeneity in biomedical data, specifically for small sample sizes.
  • To demonstrate the application of CMMs in the context of oculomotor dysfunction in schizophrenia using eye-tracking data.

Main Methods:

Related Experiment Videos

  • Comparison of FMMs and CMMs using the Expectation-Maximization (EM) algorithm.
  • Utilizing the parametric bootstrap for model fitting and comparison.
  • Application to a real-world dataset examining eye-tracking dysfunction in schizophrenia.

    • Main Results:

    • FMMs can overestimate the number of component densities when model fit is inadequate.
    • CMMs provide a viable alternative to FMMs, particularly beneficial for small sample sizes.
    • The divergence between FMMs and CMMs diminishes as the number of components in the FMM increases.

    Conclusions:

    • Continuous mixture models are a valuable alternative to finite mixture models for analyzing heterogeneous biomedical data, mitigating the risk of spurious subgroup identification.
    • The study highlights the importance of model selection in the presence of data heterogeneity and potential overfitting.
    • The findings have implications for psychiatric research, particularly in understanding complex neurobiological underpinnings of conditions like schizophrenia.