Table 3. Summary of How Well a Particular OPLS-DA Classification Model Classified the Samples into the Known Classes.
| Distribution
of Classification Results by Brand Name |
||||||||
|---|---|---|---|---|---|---|---|---|
| Sample Source | Members | Correct, % | Apotex | Kpharm | Normon | Pure | Sandoz | Teva |
| Apotex | 20 | 90.0 | 18a | 0 | 0 | 0 | 1b | 1b |
| Kpharm | 40 | 97.5 | 0 | 39a | 1b | 0 | 0 | 0 |
| Normon | 20 | 100.0 | 0 | 0 | 20a | 0 | 0 | 0 |
| Pure | 20 | 100.0 | 0 | 0 | 0 | 20a | 0 | 0 |
| Sandoz | 20 | 100.0 | 0 | 0 | 0 | 0 | 20a | 0 |
| Teva | 20 | 100.0 | 0 | 0 | 0 | 0 | 0 | 20a |
| Total | 140 | 97.9 | ||||||
Proportion of correctly classified samples in the data set.
Proportion of incorrectly classified samples.