Table 3

Summary measures of the regression models considered
Model/Statistic Main-effects Clinical Parsimonious Clinical; no age2
AIC 248 207 247 771 256 757 248 246
BIC 248 403 248 001 256 803 248 465
DoF 17 18 4 19
In-sample classification measures
Sensitivity 22.05% 17.79% 10.78% 18.91%
Specificity 98.77% 99.07% 99.24% 98.97%
AUROC 0.899 0.899 0.890 0.899
PPV 58.07% 58.29% 50.98% 57.21%
NPV 94.27% 94.30% 93.85% 94.36%
Out-of-sample classification measures
Sensitivity 22.15% 17.76% 10.94% 18.86%
Specificity 98.74% 99.06% 99.24% 98.96%
AUROC 0.898 0.898 0.889 0.898
PPV 57.23% 57.75% 50.88% 56.76%
NPV 94.33% 94.35% 93.91% 94.41%

AIC: Akaike’s Information criteria. BIC: Bayesian information criteria. DoF: Degrees of Freedom. AUROC: Area under the receiver operating characteristic curve. PPV: Positive predictive value. NPV: Negative predictive value.

Kearns et al.

Kearns et al. BMC Nephrology 2013 14:49   doi:10.1186/1471-2369-14-49

Open Data