Research Article
A Flexible Bayesian Parametric Proportional Hazard Model: Simulation and Applications to Right-Censored Healthcare Data
Table 1
Simulation results from a GLL PH framework with distributional parameters (
, , and
), covariates
.
| Posterior properties | True value | Posterior mean | Bias | Naïve SE | MSE | CP | | No. of eff |
| C = 20% | | 1.506 | 0.006 | 0.001 | 0.032 | 0.032 | 1.000 | 3782 | | 0.837 | 0.087 | 0.002 | 0.057 | 0.935 | 1.001 | 3740 | | −0.695 | 0.055 | 0.001 | 0.011 | 0.945 | 1.000 | 3720 | | 0.480 | 0.020 | 0.002 | 0.049 | 0.920 | 1.002 | 3700 | | 1.431 | 0.181 | 0.002 | 0.107 | 0.890 | 1.000 | 4039 | | 0.720 | 0.030 | 0.001 | 0.013 | 0.935 | 1.001 | 4039 |
| C = 30% | | 1.463 | −0.037 | 0.001 | 0.029 | 0.935 | 1.000 | 3802 | | 0.872 | 0.122 | 0.002 | 0.072 | 0.880 | 1.000 | 3823 | | −0.727 | 0.023 | 0.001 | 0.008 | 0.945 | 1.001 | 3761 | | 0.501 | 0.001 | 0.002 | 0.060 | 0.997 | 1.000 | 3700 | | 1.575 | 0.325 | 0.002 | 0.193 | 0.851 | 1.002 | 3865 | | 0.567 | −0.183 | 0.001 | 0.045 | 0.911 | 1.000 | 4084 |
|
|