Generation . | Layer 4 . | Layer 4 Shuffled . | p-value . | p-value < 0.05 . |
---|---|---|---|---|
30 | 0.903 | 0.837 | 0.004 | Yes |
100 | 0.936 | 0.927 | 0.601 | No |
All | 0.892 | 0.871 | 0.057 | No |
Generation . | Layer 4 . | Layer 4 Shuffled . | p-value . | p-value < 0.05 . |
---|---|---|---|---|
30 | 0.903 | 0.837 | 0.004 | Yes |
100 | 0.936 | 0.927 | 0.601 | No |
All | 0.892 | 0.871 | 0.057 | No |
Notes. The fitness of the two layers for all generations is shown in Figure 10. Layer 4 is significantly more fit than Layer 4 Shuffled in generation 30, but the difference between the two layers is no longer significant when they reach generation 100. Averaged over all the generations, the difference is not significant. The p-values are calculated using a two-tailed Welch t-test for samples with unequal variance (heteroscedastic variance).