† Cross-validation consistency is defined as the number of times the same model is identified in all 10 training data sets.
‡ Testing balanced accuracy is ((TP/(TP+FN)) + (TN/(TN+FP))/2, where TP = True Positive, FP = False Positive, TN = True Negative, and FN = False Negative. Note, testing balanced accuracy is biased unless the same locus model was identified in all 10 training data sets. Thus testing balanced is reported only when cross-validation consistency was 10/10.