TABLE 3.
Model using OCT biomarkers as predictors to predict extent of CRT improvement (ΔCRT) after treatment (multiple regression).
| Analysis of variance | ||||||
|
| ||||||
| Source | DF | Sum of squares | Mean square | AIC | F-value | Pr > F |
| Model | 1 | 122,153 | 122,153 | –151.4508 | 8.01 | 0.0063 |
| Error | 62 | 945,646 | 15,252 | –165.4669 | ||
| Corrected Total | 63 | 1,067,799 | 0.4375 | –201.8591 | ||
|
| ||||||
| Variable | Parameter estimate | Standard error | Type II SS | F-value | Pr > F | |
|
| ||||||
| Intercept | –54.00000 | 17.64292 | 142,884 | 9.37 | 0.0033 | |
| SRF | –103.13333 | 36.44305 | 122,153 | 8.01 | 0.0063 | |
*Variables included before model selection: gender, age, lens status, and all baseline OCT biomarkers.