Table 5.
Results of the 3-factor ANOVA evaluating the effects of architecture, sequence length, training method, and first-order interactions on cross-participant variance of classification accuracy. Significant results are displayed in bold.
| Source | DF | Sum of Squares | F Ratio | Prob > F |
|---|---|---|---|---|
| Architecture | 5 | 0.00033601 | 16.3957 | <0.0001 |
| Sequence Length | 1 | 0.00042976 | 104.8501 | <0.0001 |
| Training Method | 3 | 0.00001822 | 1.4816 | 0.2283 |
| Sequence Length*Training Method | 3 | 0.00037315 | 30.3464 | <0.0001 |
| Architecture*Sequence Length | 5 | 0.00011529 | 5.6258 | 0.0002 |
| Architecture*Training Method | 15 | 0.00010311 | 1.6771 | 0.0796 |