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

AIC model selection using Akaike weights.

Eric-Jan Wagenmakers1, Simon Farrell

  • 1Northwestern University, Evanston, Illinois, USA. ewagenmakers@fmg.uva.nl

Psychonomic Bulletin & Review
|May 1, 2004
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

Robust Bayesian multilevel meta-analysis: Adjusting for publication bias in the presence of dependent effect sizes.

Behavior research methods·2026
Same author

Investigating the replicability of the social and behavioural sciences.

Nature·2026
Same author

Investigating the analytical robustness of the social and behavioural sciences.

Nature·2026
Same author

Travelling through time and space in working memory.

Memory & cognition·2026
Same author

Continuous outcome estimation in N-of-1 trials for accelerated decision-making.

Epilepsia·2026
Same author

A tutorial on Bayesian hypothesis testing of correlation coefficients using the BFpack-module in JASP.

Behavior research methods·2025
Same journal

Mind wandering during first- and foreign-language reading.

Psychonomic bulletin & review·2026
Same journal

Lexical word processing is unaffected by rapid invisible frequency tagging in reading: Evidence from eye movements.

Psychonomic bulletin & review·2026
Same journal

Anxiety modulates voluntary attentional orienting to emotional gaze cues: Eye movements for pro- and anti-saccades.

Psychonomic bulletin & review·2026
Same journal

Faster key-press responses to front vowels than back vowels when matching heard vowels with represented vowels.

Psychonomic bulletin & review·2026
Same journal

Testing the interleaving effect without response bias: A forced-choice reevaluation of Kornell and Bjork (2008).

Psychonomic bulletin & review·2026
Same journal

The impact of social interaction on abstract concepts.

Psychonomic bulletin & review·2026
See all related articles

Akaike weights offer a clear probability interpretation for model comparison, improving upon raw Akaike information criterion (AIC) values. This method enhances understanding of model adequacy in research.

Area of Science:

  • Statistics
  • Cognitive Psychology
  • Model Selection

Background:

  • Akaike information criterion (AIC) is widely used for comparing statistical models.
  • Current interpretation of AIC values lacks a direct probabilistic meaning.
  • This ambiguity complicates the assessment of model adequacy in practice.

Purpose of the Study:

  • To introduce and demonstrate the utility of Akaike weights for model comparison.
  • To provide a method for interpreting AIC-based model selection in probabilistic terms.
  • To enhance the clarity and rigor of model comparison in cognitive psychology.

Main Methods:

  • Transforming raw Akaike information criterion (AIC) values into Akaike weights.
  • Utilizing established formulas for calculating Akaike weights.

Related Experiment Videos

  • Illustrating the application of Akaike weights with practical examples.

    • Main Results:

    • Akaike weights are derived from AIC values and represent conditional probabilities.
    • These weights allow for a direct and unambiguous interpretation of model comparison results.
    • The transformation facilitates a more intuitive understanding of relative model support.

    Conclusions:

    • Akaike weights provide a statistically sound and interpretable alternative to raw AIC values.
    • The proposed method significantly improves the interpretation of model comparison in cognitive psychology.
    • Adoption of Akaike weights can lead to more robust and transparent scientific conclusions.