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

Estimation of the mean and standard deviation using order statistics.

F D Dunstan1, A B Nix

  • 1School of Mathematics, University of Wales College of Cardiff, U.K.

Statistics in Medicine
|June 1, 1991
PubMed
Summary

This study explores estimating distribution parameters from censored data using order statistics. New approximations to the optimal estimator are proposed and evaluated for robustness against outliers.

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

Prevalence and pattern of cognitive impairment in a community cohort of men in South Wales: methodology and findings from the Caerphilly Prospective Study.

Neuroepidemiology·2008
Same author

A randomised controlled trial of clinical outreach education to rationalise antibiotic prescribing for acute dental pain in the primary care setting.

British dental journal·2006
Same author

Selecting specialist registrars by station interview.

Clinical medicine (London, England)·2006
Same author

Variability of antiepileptic medication taking behaviour in sudden unexplained death in epilepsy: hair analysis at autopsy.

Journal of neurology, neurosurgery, and psychiatry·2006
Same author

Differences in risk of mortality under 1 year of age between rural and urban areas: an ecological study.

Public health·2005
Same author

Are abused babies protected from further abuse?

Archives of disease in childhood·2004

Area of Science:

  • Statistics
  • Data Analysis

Background:

  • Accurate estimation of distribution parameters (mean, standard deviation) is crucial in statistical analysis.
  • Censored data, common in survival analysis and reliability, presents unique estimation challenges.
  • Order statistics provide a framework for analyzing data with missing or incomplete observations.

Purpose of the Study:

  • To discuss estimation of mean and standard deviation using linear combinations of order statistics from censored samples.
  • To compare existing methods with the optimal estimator for censored data.
  • To propose and evaluate new approximations to the optimal estimator, particularly in the presence of outliers.

Main Methods:

  • Utilizing linear combinations of order statistics for parameter estimation.
  • Comparing existing estimation techniques against a defined optimal estimator.

Related Experiment Videos

  • Employing simulation studies to assess estimator performance, especially with outlier data.

    • Main Results:

    • Identified limitations of existing methods for estimating distribution parameters from censored samples.
    • Proposed novel approximations to the optimal linear combination estimator.
    • Demonstrated the performance of these approximations in simulations, highlighting their behavior with outliers.

    Conclusions:

    • The proposed approximations offer viable alternatives for estimating distribution parameters from censored data.
    • The study provides insights into the robustness of different estimators when dealing with outliers.
    • Further research can build upon these approximations for enhanced statistical modeling with censored and outlier-prone data.