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

Problems and prediction in survival-data analysis | JoVE Visualize

Home
Research Domains
Mathematical Sciences

Problems and prediction in survival-data analysis

¹Department of Mathematics and Statistics, University of Newcastle upon Tyne, U.K.

Statistics in Medicine|January 30, 1995

View abstract on PubMed

Summary

David Cox's proportional hazards model, a key tool in survival analysis, is still widely used. This review examines its applications, limitations, and predictive accuracy compared to expert judgment.

Area of Science:

Biostatistics
Medical Statistics
Survival Analysis

Background:

David Cox's 1972 paper on 'Regression models and life tables' remains highly influential.
The proportional hazards model and partial-likelihood technique are widely applied in scientific and medical research.
Inappropriate application and irrelevant theoretical studies have arisen from the model's widespread use.

Purpose of the Study:

To review recent developments in Cox's proportional hazards model.
To discuss ongoing challenges, particularly concerning predictive inference.
To investigate the accuracy of model-based predictions versus expert judgment.

Main Methods:

Review of recent literature on proportional hazards models.
Discussion of theoretical and practical issues.
Comparative analysis of model predictions and expert judgments using a case study.

Main Results:

The proportional hazards model and partial-likelihood technique have seen extensive application.
Concerns persist regarding the appropriate use and interpretation of the model.
Model-based predictions were compared against consultant judgments in an illustrative example.

Conclusions:

Cox's proportional hazards model continues to be a cornerstone of survival data analysis.
Critical evaluation of model application and predictive accuracy is essential.
Further research is needed to refine predictive inference methods in survival analysis.

Large And Complex Data Theory

Problems And Prediction In Survival-data Analysis