Home > Research > Publications & Outputs > Predictive accuracy and explained variation in ...

Research

Links

Text available via DOI:

Keywords

View graph of relations

Predictive accuracy and explained variation in Cox regression.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Predictive accuracy and explained variation in Cox regression. / Schemper, M.; Henderson, Robin.
In: Biometrics, Vol. 56, No. 1, 2000, p. 249-255.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Schemper, M & Henderson, R 2000, 'Predictive accuracy and explained variation in Cox regression.', Biometrics, vol. 56, no. 1, pp. 249-255. https://doi.org/10.1111/j.0006-341X.2000.00249.x

APA

Schemper, M., & Henderson, R. (2000). Predictive accuracy and explained variation in Cox regression. Biometrics, 56(1), 249-255. https://doi.org/10.1111/j.0006-341X.2000.00249.x

Vancouver

Schemper M, Henderson R. Predictive accuracy and explained variation in Cox regression. Biometrics. 2000;56(1):249-255. doi: 10.1111/j.0006-341X.2000.00249.x

Author

Schemper, M. ; Henderson, Robin. / Predictive accuracy and explained variation in Cox regression. In: Biometrics. 2000 ; Vol. 56, No. 1. pp. 249-255.

Bibtex

@article{79d17c6e15984cafbb988fe8d0fdbc4b,
title = "Predictive accuracy and explained variation in Cox regression.",
abstract = "Summary. We suggest a new measure of the proportion of the variation of possibly censored survival times explained by a given proportional hazards model. The proposed measure, termed V, shares several favorable properties with an earlier V1 but also improves the handling of censoring. The statistic contrasts distance measures between individual 1/0 survival processes and fitted survival curves with and without covariate information. These distance measures, Dx and D, respectively, are themselves informative as summaries of absolute rather than relative predictive accuracy. We recommend graphical comparisons of survival curves for prognostic index groups to improve the understanding of obtained values for V, Dx, and D. Their use and interpretation is exemplified for a Yorkshire lung cancer study on survival. From this and an overview for several well-known clinical data sets, we show that the likely amount of relative or absolute predictive accuracy is often low even if there are highly significant and relatively strong prognostic factors.",
keywords = "Censored data • Cox regression • Explained variation • Prediction error • Survival analysis",
author = "M. Schemper and Robin Henderson",
year = "2000",
doi = "10.1111/j.0006-341X.2000.00249.x",
language = "English",
volume = "56",
pages = "249--255",
journal = "Biometrics",
issn = "1541-0420",
publisher = "Wiley-Blackwell",
number = "1",

}

RIS

TY - JOUR

T1 - Predictive accuracy and explained variation in Cox regression.

AU - Schemper, M.

AU - Henderson, Robin

PY - 2000

Y1 - 2000

N2 - Summary. We suggest a new measure of the proportion of the variation of possibly censored survival times explained by a given proportional hazards model. The proposed measure, termed V, shares several favorable properties with an earlier V1 but also improves the handling of censoring. The statistic contrasts distance measures between individual 1/0 survival processes and fitted survival curves with and without covariate information. These distance measures, Dx and D, respectively, are themselves informative as summaries of absolute rather than relative predictive accuracy. We recommend graphical comparisons of survival curves for prognostic index groups to improve the understanding of obtained values for V, Dx, and D. Their use and interpretation is exemplified for a Yorkshire lung cancer study on survival. From this and an overview for several well-known clinical data sets, we show that the likely amount of relative or absolute predictive accuracy is often low even if there are highly significant and relatively strong prognostic factors.

AB - Summary. We suggest a new measure of the proportion of the variation of possibly censored survival times explained by a given proportional hazards model. The proposed measure, termed V, shares several favorable properties with an earlier V1 but also improves the handling of censoring. The statistic contrasts distance measures between individual 1/0 survival processes and fitted survival curves with and without covariate information. These distance measures, Dx and D, respectively, are themselves informative as summaries of absolute rather than relative predictive accuracy. We recommend graphical comparisons of survival curves for prognostic index groups to improve the understanding of obtained values for V, Dx, and D. Their use and interpretation is exemplified for a Yorkshire lung cancer study on survival. From this and an overview for several well-known clinical data sets, we show that the likely amount of relative or absolute predictive accuracy is often low even if there are highly significant and relatively strong prognostic factors.

KW - Censored data • Cox regression • Explained variation • Prediction error • Survival analysis

U2 - 10.1111/j.0006-341X.2000.00249.x

DO - 10.1111/j.0006-341X.2000.00249.x

M3 - Journal article

VL - 56

SP - 249

EP - 255

JO - Biometrics

JF - Biometrics

SN - 1541-0420

IS - 1

ER -