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

Sensitivity analysis for informative censoring in parametric survival models.

Fotios Siannis1, John Copas, Guobing Lu

  • 1MRC Biostatistics Unit, Institute of Public Health, University Forvie Site, Robinson Way, Cambridge CB2 2SR, UK. fotios.siannis@mrc-bsu.cam.ac.uk

Biostatistics (Oxford, England)
|December 25, 2004
PubMed
Summary

Statistical analysis of censored survival data often assumes independence between lifetime and censoring. This study introduces a model accounting for dependence, showing even minor correlations can significantly impact results.

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

New Insights into Prostate Cancer Susceptibility in European Caucasians: A Systematic Review and Meta-Analysis of CYP3A4 Pharmacogene.

Cancers·2026
Same author

Clinical Characteristics and Outcomes of Traumatic Brain Injury in a High-Volume Tertiary Care Center in India: A Prospective Observational Cohort Study.

Neurosurgery·2025
Same author

Heterogeneity in meta-analysis: a comprehensive overview.

The international journal of biostatistics·2023
Same author

Automated methods to test connectedness and quantify indirectness of evidence in network meta-analysis.

Research synthesis methods·2018
Same author

Model-based sensitivity analysis for outcome reporting bias in the meta analysis of benefit and harm outcomes.

Statistical methods in medical research·2017
Same author

Borrowing of strength and study weights in multivariate and network meta-analysis.

Statistical methods in medical research·2015

Area of Science:

  • Biostatistics
  • Survival Analysis
  • Statistical Modeling

Background:

  • Standard censored survival data analysis assumes independence between event occurrence (lifetime) and censoring mechanisms.
  • This independence assumption is frequently questionable in real-world applications, potentially biasing results.

Purpose of the Study:

  • To investigate the impact of dependence between lifetime and censoring mechanisms on survival data analysis.
  • To propose and evaluate a parametric model that explicitly incorporates this dependence.

Main Methods:

  • Developed a parametric model with a dependence parameter (delta) and a bias function B(t, theta).
  • Conducted a sensitivity analysis on key parameter estimates for small values of delta.
  • Interpreted delta's magnitude as a correlation coefficient between lifetime and censoring.

Related Experiment Videos

Main Results:

  • Demonstrated that even small degrees of dependence (small delta) can lead to noticeable effects on parameter estimates.
  • Quantified the potential bias introduced by the dependence between failure and censoring processes.

Conclusions:

  • The assumption of independence in survival analysis can be misleading.
  • Acknowledge and model potential dependence between lifetime and censoring is crucial for accurate analysis, especially in medical contexts.