Table 5. Ridge-regression vs elastic-net.

par.	obs. stat.	p-value
sample size ()	42.231	<0.001
number of features ()	61.468	<0.001
saturation ()	82.652	<0.001
signal-to-noise ()	1.515	0.023
correlation ()	6.099	<0.001
sample size vs number of features ()	2.335	<0.001
sample size vs saturation ()	6.994	<0.001
sample size vs signal-to-noise ()	1.049	0.365
sample size vs correlation ()	0.675	0.996
number of features vs saturation ()	30.782	<0.001
number of features vs signal-to-noise ()	1.239	0.075
number of features vs correlation ()	1.685	<0.001
saturation vs signal-to-noise ()	1.417	0.009
saturation vs correlation ()	0.539	1.000
signal-to-noise vs correlation ()	0.739	0.967

Permutation tests for equality of the group distributions using distance components analysis (lines 2 to 6), and permutation F-tests for the presence of 2-by-2 interactions (lines 7 to 16), in the comparison of ridge-regression vs elastic-net. Results based on 999 permutations.