Table 2.
Stepwise discriminant analysis classification results
| Leaf type | Predicted group membership | Total | |||
|---|---|---|---|---|---|
| Mosaic | Semi-mosaic | Round | |||
| Trained group | % Mosaic-leaf | 98.3 | 1.7 | 0 | 100.0 |
| Semi-mosaic-leaf | 1.4 | 90.3 | 8.3 | 100.0 | |
| Round-leaf | 0 | 0 | 100.0 | 100.0 | |
| Tested group | % Mosaic-leaf | 97.5 | 2.5 | 0 | 100.0 |
| Semi-mosaic-leaf | 7.6 | 88.9 | 3.5 | 100.0 | |
| Round-leaf | 0 | 7.4 | 92.6 | 100.0 | |
| Cross-validateda | % Mosaic-leaf | 95.9 | 4.1 | 0 | 100.0 |
| Semi-mosaic-leaf | 2.1 | 89.3 | 8.7 | 100.0 | |
| Round-leaf | 0 | 1.5 | 98.5 | 100.0 | |
96.0% of trained grouped cases correctly classified
92.7% of tested grouped cases correctly classified
94.4% of cross-validated grouped cases correctly classified
aCross validation is conducted only for those cases in the analysis. In cross validation, each case is classified by the functions derived from all cases other than that case