Table 3.
Summary of canonical discriminant analysis (stepwise method).
| Step | Entered variable | Wilk’s lambda | Exact F | P-value | Standardized coefficients |
|---|---|---|---|---|---|
| 1 | BDNF | 0.768 | 59.363 | 0.000 | 0.355 |
| 2 | AGT | 0.651 | 52.431 | 0.000 | -0.459 |
| 3 | IGFBP-2 | 0.557 | 51.731 | 0.000 | 0.395 |
| 4 | OPN | 0.522 | 44.492 | 0.000 | 0.330 |
| 5 | Cathepsin D | 0.490 | 40.134 | 0.000 | 0.286 |
| 6 | SAP | 0.453 | 38.665 | 0.000 | -0.748 |
| 7 | Complement C4 | 0.410 | 39.311 | 0.000 | 0.549 |
| 8 | Prealbumin | 0.398 | 35.967 | 0.000 | 0.258 |
At each step, the variable that minimizes the overall Wilk’s lambda is entered: a. Maximum number of steps is 64; b. Minimum partial F to enter is 3.84; c. Maximum partial F to remove is 2.71; d. F level, tolerance, or VIN insufficient for further computation.