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

Multiple imputation for the Cox proportional hazards model with missing covariates

M C Paik1

  • 1Division of Biostatistics, Columbia University, New York, New York 10032, USA. mcp@biostat.columbia.edu

Lifetime Data Analysis
|January 1, 1997
PubMed
Summary

We developed three methods for handling missing data in Cox regression models. These multiple imputation techniques offer practical solutions for robust statistical analysis when covariates are incomplete.

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

Lower prevalence of silent brain infarcts in the physically active: the Northern Manhattan Study.

Neurology·2011
Same author

Quality of life declines after first ischemic stroke. The Northern Manhattan Study.

Neurology·2010
Same author

The Levels of Inflammatory Markers in the Treatment of Stroke study (LIMITS): inflammatory biomarkers as risk predictors after lacunar stroke.

International journal of stroke : official journal of the International Stroke Society·2010
Same author

Physical activity and risk of ischemic stroke in the Northern Manhattan Study.

Neurology·2009
Same author

High-sensitivity C-reactive protein predicts mortality but not stroke: the Northern Manhattan Study.

Neurology·2009
Same author

Carotid plaque, a subclinical precursor of vascular events: the Northern Manhattan Study.

Neurology·2008

Area of Science:

  • Biostatistics
  • Statistical Modeling
  • Survival Analysis

Background:

  • Missing covariate data is a common challenge in Cox regression analysis.
  • Incomplete data can lead to biased estimates and reduced statistical power.
  • Existing methods for handling missing data in survival analysis have limitations.

Purpose of the Study:

  • To introduce and evaluate three novel multiple imputation methods for the Cox model with missing covariates.
  • To provide practical and statistically sound approaches for addressing incomplete covariate data in survival analyses.
  • To compare the performance of the proposed methods with existing techniques.

Main Methods:

  • Development of three distinct multiple imputation strategies tailored for Cox proportional hazards models.

Related Experiment Videos

  • Asymptotic analysis to compare the proposed estimates with established methods as the number of imputations increases.
  • Implementation of one method using standard statistical software capable of handling time-varying covariates.

    • Main Results:

    • Two proposed multiple imputation estimates demonstrate asymptotic equivalence to existing literature estimates.
    • The third multiple imputation estimate offers a practical implementation using readily available statistical software.
    • All three methods provide valid approaches for analyzing Cox models with missing covariate data.

    Conclusions:

    • The presented multiple imputation techniques offer viable solutions for Cox models with missing covariates.
    • The third method provides a computationally feasible option for researchers using standard statistical packages.
    • These methods enhance the reliability and accuracy of survival analyses in the presence of incomplete data.