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

Dependent competing risks: a stochastic process model.

A I Yashin, K G Manton, E Stallard

    Journal of Mathematical Biology
    |January 1, 1986
    PubMed
    Summary

    This study introduces a conditional independence model for analyzing mortality data, challenging the standard assumption of independent causes of death. The findings reveal that the standard model overestimates the impact of eliminating diseases like cancer and cardiovascular disease on life expectancy.

    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

    Decomposition of disparities in life expectancy with applications to administrative health claims and registry data.

    Theoretical population biology·2023
    Same author

    Forecasting prevalence and mortality of Alzheimer's disease using the partitioning models.

    Experimental gerontology·2023
    Same author

    Underlying mechanisms of change in cancer prevalence in older U.S. adults: contributions of incidence, survival, and ascertainment at early stages.

    Cancer causes & control : CCC·2022
    Same author

    A forecasting model of disease prevalence based on the McKendrick-von Foerster equation.

    Mathematical biosciences·2019
    Same author

    Theory of partitioning of disease prevalence and mortality in observational data.

    Theoretical population biology·2017
    Same author

    Empirical Bayes Approaches to Multivariate Fuzzy Partitions.

    Multivariate behavioral research·2016

    Area of Science:

    • Biostatistics
    • Epidemiology
    • Demography

    Background:

    • Competing risk theory is crucial for analyzing mortality data by cause of death.
    • The standard approach often assumes independence between times to death from different causes.

    Purpose of the Study:

    • To develop and apply a competing risk model with conditional independence.
    • To compare results with the standard marginal independence model using Framingham Heart Study data.

    Main Methods:

    • Developed a competing risk model assuming conditional independence of death times, given a stochastic covariate process.
    • Applied the model to cause-specific mortality data.
    • Compared model outcomes against the standard marginal independence model.

    Related Experiment Videos

    Main Results:

    • The standard model overestimates the life expectancy gains from eliminating cancer (4% at age 30) and cardiovascular/cerebrovascular disease (7% at age 30).
    • Overestimations increase significantly with age: 11% for cancer and 16% for heart disease by age 80.
    • Demonstrated the potential inaccuracies of the marginal independence assumption.

    Conclusions:

    • The conditional independence model offers a more nuanced analysis of competing risks in mortality.
    • Avoiding the marginal independence assumption is vital for accurate mortality impact assessments, particularly for older populations.
    • Highlights the importance of data-driven model selection in epidemiological studies.