Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

Comparing the small sample performance of several variance estimators under competing risks.

Thomas M Braun¹, Zheng Yuan

¹Department of Biostatistics, University of Michigan, Ann Arbor, MI 48109, USA. tombraun@umich.edu

Statistics in Medicine

|August 11, 2006

Summary

Multinomial-moment variance estimators accurately estimate cumulative incidence variance, even in small samples. Martingale theory-based estimators perform poorly in small samples, making them less reliable for statistical analysis.

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

Interhospital variation in Medicare spending for infections after coronary artery bypass grafting and surgical aortic valve replacement.

JTCVS open·2026

Same author

Effectiveness of interventions to promote couples-based HIV testing and family health during pregnancy and postpartum in Kenya: a multicentre, couples-based, randomised controlled trial.

The lancet. HIV·2026

Same author

Functional specialization of two jasmonic acid-amido synthetases in rice defense and spikelet development.

The Plant cell·2026

Same author

Predictors of early response to GnRH and gonadotropin therapy in pediatric patients with suspected dual congenital hypogonadotropic hypogonadism: a retrospective single-center study.

Frontiers in endocrinology·2026

Same author

Targeting the TOPK-STAT3 pathway in keratinocytes and mast cells mediates the therapeutic attenuation of Atopic dermatitis.

Inflammation research : official journal of the European Histamine Research Society ... [et al.]·2026

Same author

Non-destructive quantification of shoot apical meristem homeostasis for prediction of plant architecture and biomass using robot-based 3D imaging and photosynthesis measurements.

Plant communications·2026

Area of Science:

Biostatistics
Statistical Modeling
Survival Analysis

Background:

Cumulative incidence estimation is crucial in survival analysis.
Variance estimation for cumulative incidence is complex, with limited comparative studies.
Existing estimators stem from martingale theory or multinomial distribution moments.

Purpose of the Study:

To compare the performance of six variance estimators for cumulative incidence.
To evaluate estimators derived from martingale theory and multinomial moments.
To assess estimator accuracy using simulations and real-world data.

Main Methods:

Comparative analysis of six variance estimators and bootstrap methods.
Simulation studies with varying sample sizes.

Related Experiment Videos

Application to real-world survival data.

Main Results:

Multinomial-moment estimators demonstrated performance comparable to bootstrap methods.
Multinomial-moment estimators are accurate even with small sample sizes (n=20).
Martingale theory-based estimators showed poor performance in small samples (n<100), with over/underestimation.

Conclusions:

Multinomial-moment variance estimators are recommended for cumulative incidence due to their accuracy and reliability.
Martingale theory-based estimators require caution in small sample settings.
Further research should focus on refining martingale-based estimators or promoting multinomial-moment approaches.