Factors effecting the model performance measures area under the ROC curve, net reclassification improvement and integrated discrimination improvement

Karaismailoglu E., Konar N. M., Goksuluk D., KARAAĞAOĞLU A. E.

COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION, cilt.48, sa.9, ss.2586-2598, 2019 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 48 Sayı: 9
  • Basım Tarihi: 2019
  • Doi Numarası: 10.1080/03610918.2018.1458135
  • Dergi Adı: COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.2586-2598
  • Anahtar Kelimeler: Delta AUC, Correlation structure, IDI, NRI, Risk prediction model, OPERATING CHARACTERISTIC CURVE, CORONARY-HEART-DISEASE, NONNESTED MODELS, RISK-FACTORS, PREDICTION, STATISTICS, MARKERS
  • Erciyes Üniversitesi Adresli: Hayır

Özet

The aim of this study is to investigate the impact of correlation structure, prevalence and effect size on the risk prediction model by using the change in the area under the receiver operating characteristic curve (Delta AUC), net reclassification improvement (NRI), and integrated discrimination improvement (IDI). In simulation study, the dataset is generated under different correlation structures, prevalences and effect sizes. We verify the simulation results with the real-data application. In conclusion, the correlation structure between the variables should be taken into account while composing a multivariable model. Negative correlation structure between independent variables is more beneficial while constructing a model.