Large-scale risk prediction applied to Genetic Analysis Workshop 17 mini-exome sequence data

BMC Proceedings

Table 6 Cross-validation error and AUC value for the empirical Bayes and random forest methods based on one replicate

Item	Model	Statistics	Empirical Bayes method	Random forest method
Cross-validation error	Gene + environment	Mean	0.26	0.23
		SE	0.009	–
AUC value	Gene + environment	Mean	0.72	0.66
		SE	0.058	–

AUC value is the area under the ROC curve when minimizing the cross-validation error. SE is the standard error of the cross-validation error and the AUC value.

ISSN: 1753-6561