Table 4.
Summary of Model comparison among Cox proportional hazard model, parametric Cox- Regression models and frailty models using AIC, BIC LR criteria
| Model | Baseline hazard | Frailty | Variance | AIC | BIC | Logliklihood |
|---|---|---|---|---|---|---|
| Cox regression | unspecified | 3339.37 | 3382.67 | --1659.68 | ||
| Weibull regression | Weibull | 1539.27 | 1591.23 | − 757.63 | ||
| Univariate frailty | Weibull | Gamma | 6.45 (p < 0.01) | 1453.07 | 1509.36 | − 713.54 |
| Univariate frailty | Weibull | Inverse-Gaussian | 5.02(p < 0.01) | 1504.51 | 1560.80 | − 739.26 |
| Shared frailty (by hospital) | Weibull | Gamma | 0.006(p = 3.08 | 1541.02 | 1597.30 | −757.51 |
| Exponential regression | exponential | 1566.57 | 1614.20 | − 772.28 | ||
| Gompertez regression | Gompertez | 1474.27 | 1526.23 | − 725.14 | ||