Computational and Mathematical Methods in Medicine / 2017 / Article / Tab 3

Research Article

Defining an Optimal Cut-Point Value in ROC Analysis: An Alternative Approach

Table 3

Relative bias and mean square error (MSE) of all methods. The normal homoscedastic balanced scenario.

Sample sizesMinimum valueYouden indexConcordance
probability
Point closest-to-(0-1) cornerIndex of Union
Relative biasMSERelative biasMSERelative biasMSERelative biasMSERelative biasMSE

0. 25500.00800.56220.30880.23580.04320.06960.03570.05130.03060.0191
1000.13030.46040.31290.16750.05880.04280.05260.03150.05050.0116
200−0.01740.36520.15100.11580.01450.02590.02210.01950.02620.0074

0.52500.00680.23070.11610.12660.00660.06760.01120.04270.01720.0265
100−0.03140.17520.07320.07830.00720.03920.00840.02580.00350.0201
200−0.00730.11900.04380.04900.00780.02420.01190.01450.01090.0153

0.84500.00400.12630.05630.0822−0.00260.0557−0.00380.0369−0.00160.0341
1000.01400.08390.04760.05380.00230.03720.00240.02190.00200.0268
200−0.00360.06310.02820.03620.00390.02370.00290.01280.00420.0214

1.28500.00110.08720.02920.06760.00150.05630.00320.04100.00330.0467
1000.00180.05580.02690.04440.00250.03680.00290.02450.00300.0336
200−0.00280.03430.01700.02480.00170.02050.00130.01190.00210.0200

,  , and was taken as 0.51, 1.05, 1.68, and 2.56, respectively.

Article of the Year Award: Outstanding research contributions of 2020, as selected by our Chief Editors. Read the winning articles.