Table 5. Comparison of an additional model including frame-specific parameters: Relative log-group Bayes factors and exceedance probabilities.
| Family 3 | Additional model | |||
|---|---|---|---|---|
| Moments and pstarve | ||||
| Model | Model | Model | Model | |
| 7 | 8 | 9 | 10 | |
| EV | EV | EV | EV | |
| pstarve | Var | Var | forage-pstarve | |
| pstarve | Skw | casino-pstarve | ||
| pstarve | ||||
| Relative log-group Bayes factors—all data (smaller is better) | 0 | 23 | 64 | -797 |
| Exceedance probabilities—all data (higher is better) | 0.0002 | 0.0001 | 0.0014 | 0.9983 |
Log-group Bayes factors based on BIC were calculated relative to the simplest model (Model 7). Smaller log-group Bayes factors indicate more evidence for the respective model versus the baseline model. The log-group Bayes factor of the winning model according to fixed-effects analysis and the highest exceedance probability according to random-effects analysis are written in bold font. BIC, Bayesian information criterion; EV, expected value; Var, variance; Skw, skewness; pstarve starvation probability