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

Table 11.

pvalues of pairwise comparison of models performance on adherence prediction using DeLong’s test

Simple RNN MLP RC RC (aggr) RC (last) LR LR (aggr) LR (last)
LSTM 3.479e−6 5.025e−12 < 2.2e−16 < 2.2e−16 < 2.2e−16 < 2.2e−16 < 2.2e−16 < 2.2e−16
Simple RNN 0.01353 7.639e−14 < 2.2e−16 < 2.2e−16 7.966e−16 < 2.2e−16 < 2.2e−16
MLP 8.937e−7 < 2.2e−16 < 2.2e−16 1.538e−8 < 2.2e−16 < 2.2e−16
RC < 2.2e−16 < 2.2e−16 2.741e−3 < 2.2e−16 < 2.2e−16
RC (aggr) 0.829 6.967e−14 0.02915 0.9102
RC (last) 3.405e−15 0.6371 0.001774
LR 1.666e−15 < 2.2e−16
LR (aggr) 0.8881

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