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

A frailty model for informative censoring.

Xuelin Huang1, Robert A Wolfe

  • 1Department of Biostatistics, University of Michigan, Ann Arbor 48109-2029, USA. xueling@umich.edu

Biometrics
|September 17, 2002
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

Long-term follow-up of oral decitabine/cedazuridine plus venetoclax for older or unfit patients with newly diagnosed acute myeloid leukemia.

Haematologica·2026
Same author

Vibecotamab for measurable residual disease in acute myeloid leukemia and for myelodysplastic syndromes and chronic myelomonocytic leukemia after hypomethylating agent failure: a phase II study.

Journal of hematology & oncology·2026
Same author

Toolkit for multistate disease progression simulation and treatment decision-making aid.

BMC medical research methodology·2026
Same author

Long-Term Outcomes of Azacitidine, Venetoclax and Gilteritinib in Newly Diagnosed FLT3-Mutated AML.

Blood advances·2026
Same author

Blinatumomab and Ponatinib Versus Hyper-CVAD and Ponatinib in Adult Patients With Newly Diagnosed Philadelphia Chromosome-Positive Acute Lymphoblastic Leukemia: A Propensity Score Analysis.

American journal of hematology·2026
Same author

Outcome of second-line therapy in adult B-cell acute lymphoblastic leukemia.

Cancer·2026

We introduce a new frailty model for clustered data, accounting for the correlation between failure and censoring. This flexible model allows for informative censoring and competing risks analysis, improving statistical accuracy.

Area of Science:

  • Biostatistics
  • Survival Analysis
  • Statistical Modeling

Background:

  • Traditional survival analysis often assumes noninformative censoring, which can lead to biased results when censoring is related to the failure event.
  • Clustered data presents unique challenges in survival analysis due to potential dependencies within clusters.
  • Existing frailty models may not adequately capture the complex relationship between failure and censoring mechanisms.

Purpose of the Study:

  • To propose a novel frailty model for clustered data that explicitly accounts for the correlation between failure and censoring.
  • To develop a flexible statistical framework that allows for informative censoring, competing risks, and varying degrees of dependence.
  • To investigate the impact of assuming noninformative censoring when it is, in fact, informative.

Related Experiment Videos

Main Methods:

  • Development of a new frailty model where the risk of censoring is influenced by the risk of failure.
  • Utilizing the Expectation-Maximization (EM) algorithm combined with Markov Chain Monte Carlo (MCMC) simulations for model fitting.
  • Conducting simulation studies to assess model performance and analyzing real-world data from kidney disease patients.

Main Results:

  • The proposed model effectively captures the dependence between failure and censoring, offering greater flexibility than traditional models.
  • The model successfully distinguishes between informative and noninformative censoring causes and handles competing risks.
  • Analyses demonstrate that incorrect assumptions of noninformative censoring can lead to significant biases.

Conclusions:

  • The new frailty model provides a robust approach for analyzing clustered survival data with informative censoring and competing risks.
  • This methodology enhances the accuracy of survival estimates by properly accounting for the relationship between failure and censoring.
  • The findings underscore the importance of assessing and modeling informative censoring in statistical analyses.