Skip to main content
Journal of Big Data

Table 3 t-test results

From: Multivariate cryptocurrency prediction: comparative analysis of three recurrent neural networks approaches

Comparison

Pearson correlation

t-stat

df

t critical (2-tailed)

Sig. (2-tailed)

LSTM vs. Bi-LSTM

 MAE

0.99998

1.01226

4

2.77645

0.36867

 RMSE

0.99998

1.00473

4

2.77645

0.37188

 MAPE

0.95813

1.19837

4

2.77645

0.29692

LSTM vs. GRU

 MAE

0.99975

0.99231

4

2.77645

0.37722

 RMSE

0.99970

0.99035

4

2.77645

0.37806

 MAPE

0.81138

0.89706

4

2.77645

0.42040

Bi-LSTM vs. GRU

 MAE

0.99987

0.97702

4

2.77645

0.38388

 RMSE

0.99984

0.98083

4

2.77645

0.38221

 MAPE

0.94161

0.46637

4

2.77645

0.66521

Back to article page