Skip to main content
Journal cover image
Tutorials in Biostatistics, Statistical Methods in Clinical Studies

Prognostic/Clinical Prediction Models: Multivariable Prognostic Models: Issues in Developing Models, Evaluating Assumptions and Adequacy, and Measuring and Reducing Errors

Publication ,  Chapter
Harrell, FE; Lee, KL; Mark, DB
August 24, 2005

Multivariable regression models are powerful tools that are used frequently in studies of clinical outcomes. These models can use a mixture of categorical and continuous variables and can handle partially observed (censored) responses. However, uncritical application of modelling techniques can result in models that poorly fit the dataset at hand, or, even more likely, inaccurately predict outcomes on new subjects. One must know how to measure qualities of a model's fit in order to avoid poorly fitted or overfitted models. Measurement of predictive accuracy can be difficult for survival time data in the presence of censoring. We discuss an easily interpretable index of predictive discrimination as well as methods for assessing calibration of predicted survival probabilities. Both types of predictive accuracy should be unbiasedly validated using bootstrapping or cross-validation, before using predictions in a new data series. We discuss some of the hazards of poorly fitted and overfitted regression models and present one modelling strategy that avoids many of the problems discussed. The methods described are applicable to all regression models, but are particularly needed for binary, ordinal, and time-to-event outcomes. Methods are illustrated with a survival analysis in prostate cancer using Cox regression.

Duke Scholars

DOI

ISBN

9780470023655

Publication Date

August 24, 2005

Volume

1

Start / End Page

223 / 249
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Harrell, F. E., Lee, K. L., & Mark, D. B. (2005). Prognostic/Clinical Prediction Models: Multivariable Prognostic Models: Issues in Developing Models, Evaluating Assumptions and Adequacy, and Measuring and Reducing Errors. In Tutorials in Biostatistics, Statistical Methods in Clinical Studies (Vol. 1, pp. 223–249). https://doi.org/10.1002/0470023678.ch2b(i)
Harrell, F. E., K. L. Lee, and D. B. Mark. “Prognostic/Clinical Prediction Models: Multivariable Prognostic Models: Issues in Developing Models, Evaluating Assumptions and Adequacy, and Measuring and Reducing Errors.” In Tutorials in Biostatistics, Statistical Methods in Clinical Studies, 1:223–49, 2005. https://doi.org/10.1002/0470023678.ch2b(i).
Harrell FE, Lee KL, Mark DB. Prognostic/Clinical Prediction Models: Multivariable Prognostic Models: Issues in Developing Models, Evaluating Assumptions and Adequacy, and Measuring and Reducing Errors. In: Tutorials in Biostatistics, Statistical Methods in Clinical Studies. 2005. p. 223–49.
Harrell, F. E., et al. “Prognostic/Clinical Prediction Models: Multivariable Prognostic Models: Issues in Developing Models, Evaluating Assumptions and Adequacy, and Measuring and Reducing Errors.” Tutorials in Biostatistics, Statistical Methods in Clinical Studies, vol. 1, 2005, pp. 223–49. Scopus, doi:10.1002/0470023678.ch2b(i).
Harrell FE, Lee KL, Mark DB. Prognostic/Clinical Prediction Models: Multivariable Prognostic Models: Issues in Developing Models, Evaluating Assumptions and Adequacy, and Measuring and Reducing Errors. Tutorials in Biostatistics, Statistical Methods in Clinical Studies. 2005. p. 223–249.
Journal cover image

DOI

ISBN

9780470023655

Publication Date

August 24, 2005

Volume

1

Start / End Page

223 / 249