Table 2.

Significant differences between models’ classification.

	Accuracy		Sensitivity		Specificity
FSAP	Linear	Quadratic	Linear	Quadratic	Linear	Quadratic
Quadratic	↓**		↓**		x
Cubic	↑**	↑**	↑*	↑**	↑**	↑**

MMP	Linear	Quadratic	Linear	Quadratic	Linear	Quadratic
Quadratic	↓**		↓**		↑*
Cubic	↑**	↑**	↑**	↑**	↑**	↑**

An independent t-test was used to test models’ differences in the mean cross-validation accuracy, sensitivity and specificity presented in Table 1. p-values were corrected for multiple comparisons using FDR. (**) represents a p-value < 0.01 and (*) a p-value < 0.05, FDA corrected non-significant contrasts are represented with an (X). Arrows ↑ and ↓ indicate if the mean of the model in the column is significantly higher or lower than the mean of the model in the row.