Figure 7From: Reliable estimation of prediction errors for QSAR models under model uncertainty using double cross-validationSolubility data: Variability of the prediction error estimates. Variability of the error estimates derived from the outer loop of double cross-validation (ave.vb (PE )) for different test data set sizes in the outer loop and for TS-PCR with different cross-validation designs in the inner loop (10-fold CV, CV -40% and CV -80%). Moderately sized test sets show the smallest variability.Back to article page