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

The Importance of Complexity in Model Selection.

Myung1

  • 1Ohio State University

Journal of Mathematical Psychology
|March 29, 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

Nitric oxide prevents the IFN-gamma/LPS-induced hepatotoxicity in a protein kinase G-independent manner.

Immunopharmacology and immunotoxicology·2001
Same author

GUEST EDITORS' INTRODUCTION.

Journal of mathematical psychology·2000
Same author

First evidence for the decay KL-->e+e- micro+ micro-

Physical review letters·1996
Same author

Instability of a two-dimensional extremal black hole.

Physical review. D, Particles and fields·1996
Same author

Blueshift of a tachyon in the charged two-dimensional black hole.

Physical review. D, Particles and fields·1995
Same author

New measurement of the CP violation parameter eta +- gamma.

Physical review letters·1995
Same journal

Corrigendum to "An entropy model of decision uncertainty" [Journal of Mathematical Psychology 125 (2025), 102919].

Journal of mathematical psychology·2025
Same journal

An entropy model of decision uncertainty.

Journal of mathematical psychology·2025
Same journal

How do people build up visual memory representations from sensory evidence? Revisiting two classic models of choice.

Journal of mathematical psychology·2024
Same journal

Experiment-based calibration in psychology: Optimal design considerations.

Journal of mathematical psychology·2024
Same journal

Expressions for Bayesian confidence of drift diffusion observers in fluctuating stimuli tasks.

Journal of mathematical psychology·2024
Same journal

A Statistical Foundation for Derived Attention.

Journal of mathematical psychology·2023
See all related articles

Selecting a mathematical model requires balancing goodness-of-fit with model complexity. Overly complex models may fit data well but fail to represent the true cognitive process, leading to poor generalization.

Area of Science:

  • Cognitive Psychology
  • Mathematical Modeling
  • Computational Neuroscience

Background:

  • Model selection in cognitive psychology aims to identify the best representation of underlying mental processes.
  • Reliance solely on goodness-of-fit can lead to selecting overly complex models.
  • Complex models may overfit data, compromising their ability to generalize.

Purpose of the Study:

  • To highlight the necessity of considering model complexity alongside goodness-of-fit in model selection.
  • To explain why selecting models based only on data fit is insufficient.
  • To demonstrate how to offset the effects of overfitting in model selection.

Main Methods:

  • Theoretical analysis of model selection principles.
  • Examination of the relationship between model complexity, data fit, and generalization.

Related Experiment Videos

  • Application of selection methods to artificial data for illustration.

    • Main Results:

    • Model selection based solely on fit results in unnecessarily complex models that overfit data.
    • Overfitting leads to poor generalization, failing to capture the true underlying process.
    • Appropriate model selection methods must counteract the impact of overfitting.

    Conclusions:

    • Effective model selection in cognitive psychology necessitates a balance between fit and complexity.
    • Overfitting is a critical issue that must be addressed by selection methodologies.
    • The presented methods offer a way to select more parsimonious and generalizable models.