Table 3.
BIC and 2loge(B10) of the models considered
| No. of Groups | BIC | Null Model | 2loge(B10) |
|---|---|---|---|
| 1 | −14586.20 | ||
| 2 | −13008.40 | 1 | 3155.6 |
| 3 | −12641.75 | 2 | 733.3 |
| 4 | −12522.83 | 3 | 237.8 |
| 5 | −12461.63 | 4 | 122.4 |
| 6 | −12417.87 | 5 | 87.52 |
| 7 | −12390.26 | 6 | 55.22 |
Note: BIC, Bayesian information criterion; 2loge(B10), twice the logarithm of the Bayes factor. The null model column represents the number of groups tested in the null hypothesis. Here, 2loge(B10) ≈ 2(ΔBIC), where ΔBIC is the BIC of the alternative (more complex) model minus the BIC of the null (simpler) model. The log form of the Bayes factor is interpreted as the degree of evidence favoring the alternative model.