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

Estimating stage occupation probabilities in non-Markov models.

Nina Gunnes1, Ornulf Borgan, Odd O Aalen

  • 1Institute of Basic Medical Sciences, Department of Biostatistics, University of Oslo, P.O. Box 1122, Blindern, 0317, Oslo, Norway. nina.gunnes@medisin.uio.no

Lifetime Data Analysis
|March 6, 2007
PubMed
Summary

This study compares two estimators for stage occupation probabilities in multistage models with dependent censoring. The Datta-Satten estimator is generally unbiased, while the Aalen-Johansen estimator can be biased but may have lower variability.

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

Adverse events following SARS-CoV-2 mRNA vaccination in norwegian adolescents.

Scientific reports·2026
Same author

Time-Dependent Mediators in Survival Analysis: Graphical Representation of Causal Assumptions.

Biometrical journal. Biometrische Zeitschrift·2026
Same author

Is indication for induction of labor associated with mode of delivery in term first births? A Norwegian registry-based study.

Acta obstetricia et gynecologica Scandinavica·2025
Same author

A direct comparison of the diagnostic accuracy of ST segment analysis (STAN) and fetal scalp blood sample lactate: A population-based observational study.

European journal of obstetrics, gynecology, and reproductive biology·2025
Same author

Multicentre double-blind randomised placebo-controlled four-arm trial to assess the effect of oral sodium bicarbonate and intravenous hyoscine butylbromide on spontaneous delivery after induction of labour in nulliparous women: protocol for the Safe Induction of Labour Trial (SAINT).

BMJ open·2025
Same author

Metabolic profiles in early pregnancy associated with metabolic pregnancy complications in women with obesity.

Journal of reproductive immunology·2024

Area of Science:

  • Biostatistics
  • Survival Analysis
  • Statistical Modeling

Background:

  • Dependent censoring complicates estimation in multistage models.
  • Covariate processes can link transition and censoring mechanisms.

Purpose of the Study:

  • To evaluate Datta-Satten and Aalen-Johansen estimators for stage occupation probabilities under dependent censoring.
  • To compare bias and variability of these estimators.

Main Methods:

  • Applied an additive hazard regression model to adjust for dependent censoring.
  • Utilized inverse probability of censoring weighting for observed processes.
  • Conducted simulation studies using frailty models.

Main Results:

  • The Datta-Satten estimator demonstrated approximate unbiasedness.

Related Experiment Videos

  • The Aalen-Johansen estimator showed bias due to dependent censoring.
  • The Aalen-Johansen estimator exhibited slightly smaller mean squared error in simulations.
  • Conclusions:

    • The Datta-Satten estimator is reliable for stage occupation probability estimation.
    • Practical deviations between estimators require highly selective censoring mechanisms.