Table 5.
Treatment rankings, the probability of being the best treatment, under the considered Bayesian
| Model and prior | Trt1 | Trt2 | Trt3 | Trt4 |
|---|---|---|---|---|
|
Weakly informed variances models |
|
|
|
|
|
Homogeneous variance |
0.00% |
28.2% |
0.00% |
71.8% |
| Unrestricted variances |
0.01% |
56.8% |
0.00% |
43.2% |
| Exchangeable variances |
0.01% |
49.3% |
0.02% |
50.4% |
| Consistency variances structure |
0.04% |
45.0% |
0.01% |
55.9% |
|
Moderately informed variances models |
|
|
|
|
| Frequentist informed priors |
0.00% |
42.5% |
0.00% |
57.5% |
| Empirically informed priors | 0.00% | 46.5% | 0.00% | 53.5% |
MTC models for the second illustrative example.