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

Marker selection by Akaike information criterion and Bayesian information criterion.

W Li1, D R Nyholt

  • 1Laboratory of Statistical Genetics, Rockefeller University, Box 192, 1230 York Avenue, New York, NY 10021, USA.

Genetic Epidemiology
|January 17, 2002
PubMed
Summary

Discriminant analysis using identity by descent (IBD) markers identified key genetic factors for asthma. Model comparison criteria like Akaike information criterion (AIC) and Bayesian information criterion (BIC) improved selection accuracy over single-locus scores.

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

Author Correction: Genome-wide association and epidemiological analyses reveal common genetic origins between uterine leiomyomata and endometriosis.

Nature communications·2022
Same author

Genetic overlap analysis of endometriosis and asthma identifies shared loci implicating sex hormones and thyroid signalling pathways.

Human reproduction (Oxford, England)·2022
Same author

Genome-wide association and epidemiological analyses reveal common genetic origins between uterine leiomyomata and endometriosis.

Nature communications·2019
Same author

A continuum of genetic liability for minor and major depression.

Translational psychiatry·2017
Same author

Short telomere length is associated with impaired cognitive performance in European ancestry cohorts.

Translational psychiatry·2017
Same author

Genetic effects influencing risk for major depressive disorder in China and Europe.

Translational psychiatry·2017

Area of Science:

  • Genetics
  • Statistical Genetics
  • Bioinformatics

Background:

  • Genetic studies often rely on identifying specific markers associated with diseases.
  • Sibling pair analysis is a common method for studying heritable traits.
  • Statistical model selection is crucial for accurate interpretation of genetic data.

Purpose of the Study:

  • To apply discriminant analysis using identity by descent (IBD) markers to predict sib pair type.
  • To evaluate the utility of Akaike information criterion (AIC) and Bayesian information criterion (BIC) for model selection in genetic association studies.
  • To identify a parsimonious set of genetic markers associated with asthma in a German cohort.

Main Methods:

  • Discriminant analysis was performed with IBD at each marker as input and sib pair type as output.

Related Experiment Videos

  • Logistic regression was used for discriminant analysis, emphasizing model comparison.
  • Stepwise variable selection was implemented using AIC and BIC criteria on the German Asthma dataset.

    • Main Results:

    • The study highlights the importance of comparing statistical models with varying numbers of parameters.
    • AIC and BIC stepwise selection identified a set of 25-26 markers providing the best fit for asthma data, assuming an additive effect.
    • The selected markers differed from those with the highest single-locus lod scores, suggesting a more complex genetic architecture.

    Conclusions:

    • Discriminant analysis with IBD markers, guided by AIC/BIC model selection, effectively identifies relevant genetic markers for complex diseases like asthma.
    • This approach offers a more robust method for genetic marker selection compared to relying solely on single-locus lod scores.
    • The findings underscore the value of sophisticated statistical modeling in unraveling the genetic basis of diseases.