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

Density estimation applications for outlier detection.

M E Tarter

    Computer Programs in Biomedicine
    |July 1, 1979
    PubMed
    Summary

    This study introduces a new method for identifying unusual data points using probability density estimation. It helps researchers visualize and interpret outliers in complex, multi-dimensional datasets more effectively.

    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

    Conditional switching: a new variety of regression with many potential environmental applications.

    Environmental health perspectives·1995
    Same author

    Answers to some questions raised by the presentation on the graphical analysis of the interrelationships between waterborne asbestos, digestive system cancer and population density.

    Environmental health perspectives·1983
    Same author

    A graphical analysis of the interrelationships among waterborne asbestos, digestive system cancer and population density.

    Environmental health perspectives·1983
    Same author

    Biocomputational methodology an adjunct to theory and applications.

    Biometrics·1979
    Same author

    Interactive graphical isolation of homogeneous data subgroups.

    Computer programs in biomedicine·1978
    Same author

    Interactive editing of biomedical data.

    Computer programs in biomedicine·1976

    Area of Science:

    • Biostatistics
    • Data Analysis
    • Medical Informatics

    Background:

    • Interpreting normal ranges in multi-dimensional biomedical data is challenging.
    • Identifying outliers often relies on subjective or limited univariate methods.
    • Existing outlier detection procedures can be difficult to generalize.

    Purpose of the Study:

    • To develop a novel method for outlier detection in biomedical research.
    • To enable researchers to visualize the probability of data point recurrence.
    • To provide a more interpretable and generalizable approach to identifying abnormal values.

    Main Methods:

    • Utilized nonparametric estimation of joint, conditional, and marginal probability densities.
    • Implemented an interactive graphical procedure for data visualization.
    • Displayed both the estimated probability and numerical coordinates of data points.

    Main Results:

    • The procedure effectively estimates the relative probability of data point recurrence.
    • Visualizing probability alongside coordinates aids in outlier identification.
    • The method circumvents the difficulties of interpreting multi-dimensional normal ranges.

    Conclusions:

    • This approach offers a more intuitive and generalizable method for outlier detection in biomedical research.
    • It enhances the ability of researchers to identify unusual or abnormal data points.
    • The interactive graphical system facilitates better understanding of complex datasets.

    Related Experiment Videos