On the optimism correction of the area under the receiver operating characteristic curve in logistic prediction models

Iparragirre, Amaia; Barrio, Irantzu; Rodríguez Álvarez, María Xosé

Abstract:

When the same data are used to fit a model and estimate its predictive performance, this estimate may be optimistic, and its correction is required. The aim of this work is to compare the behaviour of different methods proposed in the literature when correcting for the optimism of the estimated area under the receiver operating characteristic curve in logistic regression models. A simulation study (where the theoretical model is known) is conducted considering different number of covariates, sample size, prevalence and correlation among covariates. The results suggest the use of k-fold cross-validation with replication and bootstrap. © 2019 Institut d'Estadistica de Catalunya. All rights reserved.

Year:

2019

Type of Publication:

Article

Keywords:

Area under the receiver operating characteristic curve; Bootstrap; Logistic regression; Prediction models; Validation

Journal:

Sort

Volume:

43

Number:

1

Pages:

145-162

Month:

January-June

Note:

Q2 58/123 h-index 1.125 (JCR2018)

Comments:

This study was partially supported by grants Severo Ochoa Program SEV-2013-0323, Basque Government BERC Program 2018-2021, IT620-13 from the Departamento de Educación, Política Lingüística y Cultura del Gobierno Vasco and through project MTM2017-82379-R funded by (AEI/FEDER, UE) and acronym “AFTERAM”, and projects MTM2014-55966-P and MTM2016-74931-P from the Ministerio de Economía y Competitividad and FEDER. Amaia Iparragirre was partially supported by an Inter-ship Position at BCAM - Basque Centre for Applied Mathematics.

DOI:

10.2436/20.8080.02.82