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

Maximum likelihood estimation for tied survival data under Cox regression model via EM-algorithm.

Thomas H Scheike1, Yanqing Sun

  • 1Department of Biostatistics, University of Copenhagen, Øster Farimagsgade 5 B, 1014, Copenhagen K, Denmark. ts@biostat.ku.dk

Lifetime Data Analysis
|August 9, 2007
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

Metabolic-epigenetic crosstalk in lung cancer: Glycolytic reprogramming and lactylation-driven macrophage polarization.

Pathology, research and practice·2026
Same author

Split-Dose Versus Standard Single-Dose Bowel Preparation Regimens for Colonoscopy: A Systematic Review and Meta-Analysis.

Cureus·2026
Same author

Integrative genomic analysis identifies key target genes and candidate drugs for spinal stenosis.

Frontiers in molecular neuroscience·2026
Same author

Comparative Efficacy and Safety of Remimazolam Versus Propofol for Sedation in Gastrointestinal Endoscopy: A Systematic Review and Meta-Analysis.

Cureus·2026
Same author

Pollution Characteristics and Risk Assessment of Chlorinated Paraffins in Seawater and Kelp from Kelp Mariculture Areas of the Shandong Peninsula.

Toxics·2026
Same author

FA-2-b-β modulates HMGB1/NF-κB/NLRP3 signaling to alleviate neuroinflammation in Alzheimer's disease.

Journal of Alzheimer's disease : JAD·2026
Same journal

Shared frailty sieve estimation for dependent left truncated and interval censored data.

Lifetime data analysis·2026
Same journal

Functional win-fractions regression models for composite outcomes.

Lifetime data analysis·2026
Same journal

Variable selection in causal semiparametric transformation models with all-or-nothing treatment compliance.

Lifetime data analysis·2026
Same journal

Correction to: A uniformisation-driven algorithm for inference-related estimation of a phase-type ageing model.

Lifetime data analysis·2026
Same journal

Unobserved heterogeneity in threshold regression based on the hitting times of a reflected Brownian motion for recurrent hypoglycemia.

Lifetime data analysis·2026
Same journal

Variable selection with broken adaptive ridge regression for interval-censored competing risks data.

Lifetime data analysis·2026
See all related articles

This study introduces a new method for analyzing tied survival data using the Cox proportional regression model, improving estimation accuracy over existing approaches. The novel EM-algorithm based method offers unbiased estimates and comparable asymptotic properties to standard techniques.

Area of Science:

  • Biostatistics
  • Survival Analysis
  • Statistical Modeling

Background:

  • Standard methods for tied survival data (Breslow, Efron, exact methods) can yield biased estimates under the Cox proportional regression model.
  • Existing approaches may not accurately reflect the true underlying statistical model when data ties are present.

Purpose of the Study:

  • To review existing methods for handling tied survival data within the Cox proportional regression framework.
  • To propose a novel, unbiased method for analyzing tied survival data using the expectation-maximization (EM) algorithm.
  • To compare the finite sample properties of the new method against established techniques via simulation.

Main Methods:

  • Review of Breslow and Efron approximations and exact methods for tied survival data.

Related Experiment Videos

  • Development of a new method employing the missing-data principle and the EM-algorithm.
  • Derivation of a score equation with a mean of zero for direct solution.
  • Conducting a simulation study to evaluate finite sample performance.

    • Main Results:

    • The proposed EM-algorithm based method provides unbiased estimates for tied survival data under the Cox model.
    • All considered methods exhibit identical asymptotic properties.
    • No asymptotic efficiency is lost, irrespective of tie size bounds or convergence rates.

    Conclusions:

    • The novel EM-algorithm approach offers an unbiased alternative for analyzing tied survival data in Cox regression.
    • The method demonstrates robust performance and maintains asymptotic efficiency, making it suitable for various tie scenarios.
    • Simulation results confirm the practical utility and advantages of the proposed method over traditional approximations.