Summary of cross-validation results after constructing five sets (labelled A–E), showing the predictive accuracy when the set is excluded from the training set for Model 2.

Empirical significance was obtained from the fraction of permutations that showed a correlation higher than in the real data.

经验显著性（empirical significance）可通过统计置换样本中相关系数高于真实数据的置换比例得到。