Research Article
An Empirical Study of the Effect of Power Law Distribution on the Interpretation of OO Metrics
Table 21
Classification performance for the three data sets.
| ā | Precision | Recall | -measure* |
| CBO ā„ 17 | 70% | 83% | 76% | CBO < 17 | 51% | 50% | 50% | CBO | 58% | 60% | 59% |
| NOC 2 | 8% | 7% | 7% | NOC < 2 | 57% | 100% | 72% | NOC | 56% | 94% | 70% |
| RFC 24 | 66% | 66% | 66% | RFC < 24 | 50% | 35% | 41% | RFC | 62% | 58% | 60% |
| WMC 17 | 81% | 88% | 84% | WMC < 17 | 56% | 48% | 52% | WMC | 63% | 51% | 56% |
| LOC 235 | 78% | 82% | 80% | LOC < 235 | 52% | 50% | 51% | LOC | 62% | 64% | 63% |
| NOM 11 | 78% | 85% | 81% | NOM < 11 | 62% | 66% | 64% | NOM | 62% | 72% | 67% |
|
|
*The NOV is not available in the Promise data.
|