Table 6. Rank differences and p-values for pair-wise comparison of encodings.
Hypothesis | Rank diff | p-value |
---|---|---|
Add vs Gen | 0.82 | < 10−15 |
Add vs Rec | 0.58 | 1.765 ⋅ 10−12 |
Rec vs Gen | 0.23 | 0.004434 |
For each pair-wise comparison of encodings, the rank difference was calculated as the difference of the average ranks over all data sets and algorithms. The first encoding of each hypothesis is the better one (lower rank). p-values were corrected using Shaffer’s static method.