Skip to main content
. 2022 Nov 29;22:313. doi: 10.1186/s12911-022-02052-9

Table 12.

p values of pairwise comparison of models performance on 1000 (repeats) randomly resampled with replacement test sets (10,096 samples) using Kolmogorov–Smirnov test

Simple RNN MLP RC RC (aggr) RC (last) LR LR (aggr) LR (last)
LSTM 3.581e−149 1.366e−298 0.0 0.0 0.0 0.0 0.0 0.0
Simple RNN 5.819e−62 0.0 0.0 0.0 0.0 0.0 0.0
MLP 2.441e−255 0.0 0.0 0.0 0.0 0.0
RC 0.0 0.0 3.683e−19 0.0 0.0
RC (aggr) 0.01960 0.0 2.029e−3 0.08690
RC (last) 0.0 2.462e−7 7.336e−5
LR 0.0 0.0
LR (aggr) 0.1641

Using significance level of 0.05, values under the Bonferroni adjusted significance level of 0.00139 are in bold