1Center for Mathematical Sciences - DST, C.R.Rao Advanced Institute of Mathematics Statistics and Computer Science (AIMSCS), UoH Campus, Hyderabad-500 046.
2Department of Statistics, Sri Venkateswara Univeristy, Tirupati-517 502.
While comparing effectiveness of several biomarkers as determinants of a disease, it is observed that the obtained area under the receiver operating characteristic (ROC) curve has a similar behavior like that of the odds ratio (OR) obtained from binary logistic regression. For a biomarker if the OR is high (low), the area under the curve (AUC) of ROC is also high (low). This paper reports some empirical results on the functional relationship between AUC and OR by using simulated data. Spreadsheets-based templates are also developed to perform the calculations.
AUC, Odds Ratio, ROC Curve and Logistic Regression