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

The analysis of rates using Poisson regression models.

E L Frome

    Biometrics
    |September 1, 1983
    PubMed
    Summary

    This study introduces Poisson regression models for event rate analysis using iteratively reweighted least squares (IRLS). This method provides maximum likelihood estimates and aids in detecting data anomalies for regression modeling.

    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

    Detection of beryllium sensitivity using a flow cytometric lymphocyte proliferation test: the Immuno-Be-LPT.

    Toxicology·2001
    Same author

    A mortality study of employees of the nuclear industry in Oak Ridge, Tennessee.

    Radiation research·1997
    Same author

    A method for estimating occupational radiation dose to individuals, using weekly dosimetry data.

    Radiation research·1997
    Same author

    Statistical methods for the blood beryllium lymphocyte proliferation test.

    Environmental health perspectives·1996
    Same author

    Job factors, radiation and cancer mortality at Oak Ridge National Laboratory: follow-up through 1984.

    American journal of industrial medicine·1993
    Same author

    Concentration-dependent protection against X-ray-induced chromosome aberrations in human lymphocytes by the aminothiol WR-1065.

    Radiation research·1993

    Area of Science:

    • Biostatistics
    • Epidemiology
    • Statistical Modeling

    Background:

    • Regression models are crucial for understanding relationships between variables.
    • Poisson distribution is often used for count data or event rates.
    • Existing methods may lack flexibility for complex event rate modeling.

    Purpose of the Study:

    • To present a flexible Poisson regression modeling approach for event rate analysis.
    • To demonstrate the utility of iteratively reweighted least squares (IRLS) for parameter estimation.
    • To apply the method to real-world epidemiological data.

    Main Methods:

    • Utilized iteratively reweighted least squares (IRLS) for parameter estimation in Poisson regression.
    • Equated IRLS to the method of scoring for maximum likelihood (ML) estimates under Poisson distribution.
    • Incorporated diagnostic measures for identifying outlying responses and extreme data points.

    Main Results:

    • IRLS provides ML estimates and asymptotic covariance matrices for Poisson regression models.
    • The approach accommodates log-linear, quasilinear, and nonlinear models.
    • Demonstrated application in analyzing lung cancer death rates using a nonlinear carcinogenesis model.

    Conclusions:

    • The proposed IRLS-based Poisson regression framework offers a robust method for analyzing event rates.
    • Standard statistical packages can implement these models for ML estimation and diagnostics.
    • The methodology is applicable to epidemiological studies, including life-table analyses.

    Related Experiment Videos