Jove
Visualize
Contact Us

Related Experiment Videos

Nonparametric regression to the mean.

Hans-Georg Muller1, Ian Abramson, Rahman Azari

  • 1Department of Statistics, University of California, 1 Shields Avenue, Davis, CA 95616, USA. mueller@wald.ucdavis.edu

Proceedings of the National Academy of Sciences of the United States of America
|August 7, 2003
PubMed
Summary

This study addresses the regression-to-the-mean problem, where data includes errors. A new nonparametric method is introduced for accurate prediction when error distributions are unknown, improving upon classical solutions.

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

Brain volume trajectories in young children are associated with polygenic scores for late-onset Alzheimer's disease risk.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026
Same author

Wasserstein regression with empirical measures and density estimation for sparse data.

Biometrics·2024
Same author

Longitudinal activity monitoring and lifespan: quantifying the interface.

Aging·2024
Same author

Gradient synchronization for multivariate functional data, with application to brain connectivity.

Journal of the Royal Statistical Society. Series B, Statistical methodology·2024
Same author

Daily activity profiles over the lifespan of female medflies as biomarkers of aging and longevity.

Aging cell·2024
Same author

A Review of Potential Electrochemical Applications in Buildings for Energy Capture and Storage.

Micromachines·2023
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

Area of Science:

  • Statistics
  • Data Analysis
  • Measurement Error

Background:

  • Measurement errors are common in data, leading to the regression-to-the-mean problem.
  • Classical solutions exist for normal distributions but fail when distributions are unknown.

Purpose of the Study:

  • To extend regression-to-the-mean solutions to scenarios with unknown error distributions.
  • To develop a nonparametric approach for accurate prediction with contaminated data.

Main Methods:

  • Investigated extensions of the classical regression-to-the-mean formula.
  • Developed a fully nonparametric solution for small contaminating errors.
  • Utilized a data-sharpening algorithm based on local sample means.

Main Results:

Related Experiment Videos

  • A nonparametric regression-to-the-mean paradigm was successfully developed.
  • The method is implementable via a straightforward data-sharpening algorithm.
  • Asymptotic justifications and practical examples support the findings.

Conclusions:

  • The new nonparametric method offers a robust solution for regression-to-the-mean problems with unknown distributions.
  • This approach enhances prediction accuracy in the presence of measurement errors.
  • The data-sharpening algorithm provides a practical tool for implementation.