Table 7.
Statistical significance tests for port throughput when the relative ratio of the training sample size is 80% (panel A: DM test, panel B: PT test)
| i j = | A: DM test (p-value) | B: PT test (p-value) | |||||
|---|---|---|---|---|---|---|---|
| Proposed | SARIMA | RNN | LSTM | GRU | Method | Results | |
| Proposed | – | 0.0018 | 0.0000 | 0.0000 | 0.0009 | Proposed | 0.0000 |
| SARIMA | – | 0.0078 | 0.0137 | 0.3021 | SARIMA | 0.0000 | |
| RNN | – | 0.0010 | 0.0000 | RNN | 0.0000 | ||
| LSTM | – | 0.0000 | LSTM | 0.0000 | |||
| GRU | – | GRU | 0.0000 | ||||