Model | LogL | npar | AIC | p-val (LR) | FS_g | PDS_g | H_g | BA_g | FI_b | PDS_b | H_b | BA_b |
|---|
Null | − 18,880.5 | 19 | 37,798.9 | - | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
Full | − 18,676.1 | 27 | 37,406.1 | 2.43E-83* | 1 | 1 | 1 | 1 | 1 | 1 | 1 | 1 |
Best | − 18,677.2 | 24 | 37,402.5 | 0.497** | 1 | 1 | 0 | 0 | 1 | 1 | 0 | 1 |
- LogL log-likelihood, npar number of parameters, AIC Akaike information criterion, p-val (LR) p value of the likelihood ratio test; selection gradient series: FI flower intensity, FS fruit set, PDS percent damage score, H height, BA basal area, g (gamma) female selection gradient, b (beta) male selection gradient, 1/0 included/excluded selection gradient
- *p value of the LR test for the difference in fit between the null and full model
- **p value of the LR test for the difference in fit between the full and the best model according to the backward elimination procedure
