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

On the issue of 'multiple' first failures in competing risks analysis.

Bee-Choo Tai1, Ian R White, Val Gebski

  • 1NMRC Clinical Trials and Epidemiology Research Unit, 10 College Road, Singapore 169851. taibc@cteru.gov.sg

Statistics in Medicine
|September 5, 2002
PubMed
Summary

This study addresses tied events in competing risks analysis for cancer trials. New methods like weighting and jittering offer alternatives to existing approaches for handling multiple first recurrences, improving statistical accuracy.

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

Cuboid dislocations: Short and long term results and a review of the literature.

Foot (Edinburgh, Scotland)·2026
Same author

Estimating treatment effect in randomised controlled trials with continuous outcomes subject to non-compliance: a logistic regression-based multiple imputation approach.

Trials·2025
Same author

Pragmatic Interventions to Boost Surveillance Mammogram Uptake Among an Overdue Population: A Randomized Clinical Trial.

JAMA internal medicine·2025
Same author

A novel strategy for conversion from pediatric V-A ECMO to CPB circuit.

The journal of extra-corporeal technology·2025
Same author

International neuroblastoma risk group consortium: a model of networking for rare cancers.

Journal of the National Cancer Institute·2025
Same author

Restricted mean survival time approach versus time-varying coefficient Cox model for quantifying treatment effect when hazards are non-proportional.

BMC medical research methodology·2025

Area of Science:

  • Biostatistics
  • Clinical Trials
  • Cancer Research

Background:

  • Classical competing risks analysis assumes single failure events.
  • Cancer trials may encounter multiple first recurrences (tied events) at follow-up.
  • Existing methods struggle with substantial tied events in competing risks models.

Purpose of the Study:

  • To evaluate methods for handling tied first failure events in competing risks analysis.
  • To compare novel approaches with existing methods using osteosarcoma trial data.

Main Methods:

  • Introduced a weighting factor (reciprocal of the number of ties) to address tied events.
  • Explored 'jittering' by randomly adjusting tied event times to break ties.
  • Compared these methods to Arriagada et al.'s approach of combining simultaneous failures.

Related Experiment Videos

Main Results:

  • Arriagada's method resulted in larger standard errors for estimates.
  • Weighted and jittering methods produced similar estimates.
  • Jittering is broadly applicable but computationally intensive.
  • Weighted Cox approach is efficient if supported by statistical software.

Conclusions:

  • The weighted Cox approach and jittering are viable alternatives for tied events in competing risks.
  • Method choice depends on statistical software support and computational resources.
  • Accurate handling of tied events is crucial for reliable competing risks analysis in cancer trials.