Table 4.
Statistic | Decision Tree | CVA {pah} | CVA {pss} | CVA {ms} | CVA {cc} | CVA {ec} | CVA {all} | SWDA {all} | Simplified Model |
488 | |||||||||
Accuracy | 95.5 | 100.0 | 99.6 | 99.6 | 98.4 | 99.8 | 100.0 | 99.2 | 99.0 |
Coefficient | 94.7 | 100.0 | 99.5 | 99.5 | 98.1 | 99.8 | 100.0 | 99.1 | 98.8 |
Unclassified | 0 | 4 | 4 | 4 | 4 | 4 | 4 | 2 | 8 |
198 | |||||||||
Accuracy | 92.9 | 96.1 | 96.1 | 97.2 | 93.9 | 96.1 | 95.0 | 95.4 | 96.4 |
Coefficient | 92.0 | 95.6 | 95.6 | 96.8 | 93.0 | 95.6 | 94.3 | 94.8 | 95.9 |
Unclassified | 0 | 19 | 19 | 19 | 19 | 19 | 19 | 3 | 3 |
Note.—The accuracy and coefficient of agreement are reported for the Decision Tree, SWDA{all}, each CVA, and the Simplified Model classification methods. The measures are derived from two data sets. The first measurements are based on the 488 fungal sequences used in building the models. The second set assesses the models on with the F.198 sequence set. The number of sequences that were unable to be classified (Unclassified) for each model are also reported.