Table 4. Ranked linear mixed-effects models of anemone size explained by date, bleaching category (bleach_cat) and the interaction between these two variables.
| Model | k | LL | AICc | ΔAICc | wAICc |
| Size∼date×bleach_cat+(1|id) | 6 | −186 | 390.73 | 0 | 1 |
| Size∼date+bleach_cat+(1|id) | 4 | −200.5 | 414.31 | 23.57 | <0.01 |
| Size∼date+(1|id) | 3 | −208.8 | 428.28 | 37.55 | <0.01 |
| Size∼bleach_cat+(1|id) | 2 | −211.9 | 432.15 | 41.42 | <0.01 |
| Size∼1+(1|id) | 1 | −219.7 | 445.57 | 54.84 | <0.01 |
All models have individual colony coded as a random effect (1|id). The models are ranked against the intercept-only model (NULL model). Also shown is the number of estimable model parameters (k), maximum log-likelihood (LL), Akaike’s information criterion corrected for small samples (AICc), the difference in AICc for each model from the top-ranked model (ΔAIC) and the model weight (wAICc).