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

Survival curve estimation with partial non-random exposure information.

Ron Brookmeyer1, Frank C Curriero

  • 1Johns Hopkins University, School of Hygiene and Public Health, Department of Biostatistics, 615 North Wolfe Street, Baltimore, Maryland 21205, USA. rbrook@jhsph.edu

Statistics in Medicine
|September 14, 2002
PubMed
Summary

This study estimates survival curves for Alzheimer's disease patients with and without the apolipoprotein E4 allele, even with incomplete genetic data and censored observations. Methods address missing genetic information not missing at random.

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

Prognostic Value of Blood-Based P-Tau217 Levels for Progression to Cognitive Impairment.

JAMA·2026
Same author

APOE-ε4 carriership and dementia risk over 10 years among Asian American and White older adults.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026
Same author

Demonstrating the potential for utilizing mobile methadone units to serve medically institutionalized populations in New York State.

Journal of substance use and addiction treatment·2026
Same author

Geospatial variation and risk factors for malnutrition among postpartum women in rural Bangladesh.

PLOS global public health·2026
Same author

Seasonal stratification of anopheline abundance and species composition in southern Zambia suggests year-round, season-specific vector control approaches are needed.

Malaria journal·2025
Same author

Malaria outbreak prediction at the sub-district level in Zambia using remote sensing satellite data.

Malaria journal·2025

Area of Science:

  • Biostatistics
  • Epidemiology
  • Genetics

Background:

  • Estimating survival curves is crucial in medical research, but often complicated by missing data.
  • Left truncation and right censoring are common challenges in survival analysis.
  • Incomplete exposure group data, where missingness depends on censoring status (not missing at random), presents a significant analytical hurdle.

Purpose of the Study:

  • To develop a statistical method for estimating survival curves when exposure group status is partially unknown.
  • To address data with both left truncation and right censoring, and non-randomly missing exposure data.
  • To apply these methods to a real-world Alzheimer's disease study.

Main Methods:

  • Utilized an Expectation-Maximization (EM) algorithm for survival curve estimation in discrete time.

Related Experiment Videos

  • Developed a bootstrapping procedure to ensure consistent proportions of missing exposure data in samples.
  • Employed simulation studies to assess estimator bias and evaluate design/efficiency.

    • Main Results:

    • The proposed EM algorithm and bootstrapping procedure provide a robust method for handling complex survival data.
    • Simulations demonstrated the effectiveness of the estimators in addressing bias.
    • The methods were successfully applied to Alzheimer's disease data.

    Conclusions:

    • The developed methodology effectively estimates survival curves in the presence of non-randomly missing exposure data, left truncation, and right censoring.
    • This approach is valuable for epidemiological studies, particularly in complex genetic association studies like the Alzheimer's disease example.
    • Accurate survival estimation is critical for understanding disease progression and risk factors.