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

Hypothesis testing of time-dependent recurrent events.

J C Niland1, D Thomas, S P Azen

  • 1Department of Preventive Medicine, USC School of Medicine, Los Angeles 90033.

Statistics in Medicine
|September 1, 1987
PubMed
Summary
This summary is machine-generated.

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

Team nursing.

Nursing times·1992
Same author

Lack of platelet-activating factor release during reversible myocardial ischaemia.

European heart journal·1992
Same author

[Diagnostic and therapeutic strategy in patients with multiple arterial disease].

Annales de cardiologie et d'angeiologie·1992
Same author

Risk assessment for aflatoxin B1: a modeling approach.

Risk analysis : an official publication of the Society for Risk Analysis·1992
Same author

Comparison of skin changes induced on mice by either group A type 12 or group G streptococci.

Experimental dermatology·1992
Same author

IBIS integrated biological imaging system: electron micrograph image-processing software running on Unix workstations.

Computer applications in the biosciences : CABIOS·1992

Comparing time-dependent recurrent events between groups requires careful hypothesis testing. Two advanced methods, generalized Poisson and risk score tests, are appropriate when data has autocorrelation or heterogeneous risk, unlike the simple chi-square test.

Area of Science:

  • Biostatistics
  • Epidemiology
  • Medical Statistics

Background:

  • Comparing time-dependent recurrent events across exposure groups is crucial in medical research.
  • Standard statistical methods may fail when data exhibits autocorrelation or heterogeneous risk.
  • Accurate hypothesis testing is essential for reliable epidemiological studies.

Purpose of the Study:

  • To evaluate hypothesis testing methods for comparing recurrent event data between exposure groups.
  • To assess method performance under conditions of autocorrelation and heterogeneous risk.
  • To identify robust and practical statistical approaches for epidemiological analysis.

Main Methods:

  • Comparison of three hypothesis testing methods: generalized simple Poisson chi-square, generalized compound Poisson chi-square, and risk score tests.

Related Experiment Videos

  • Simulation study to assess method performance with simulated autocorrelated and heterogeneous risk data.
  • Application of methods to a real-world cohort of sickle cell anaemia patients.

    • Main Results:

    • The simple chi-square test is inadequate when autocorrelation or heterogeneous risk is present.
    • Generalized Poisson and risk score tests demonstrate strong performance in these complex scenarios.
    • The risk score method offers a practical advantage due to its ease of application.

    Conclusions:

    • For time-dependent recurrent events with autocorrelation or heterogeneous risk, generalized Poisson or risk score tests are recommended.
    • The risk score method provides a reliable and user-friendly alternative for hypothesis testing in such cases.
    • These findings improve the accuracy of comparative analyses in epidemiological and clinical studies.