A Flexible Bayesian Parametric Proportional Hazard Model: Simulation and Applications to Right-Censored Healthcare Data

Table 5

Numerical summaries of posterior characteristics based on McMC sample of the GLL PH model for the lung cancer data set.

Characteristics	Pars
	Alpha	(diagt)	(age)	(prior)	(trt)	Eta	Kappa
Mean	1.317	0.002	−0.024	−0.015	−0.151	0.042	0.103
SD	0.173	0.010	0.008	0.021	0.178	0.015	0.049
Naïve SE	0.001	0.0001	0.0001	0.0002	0.001	0.0001	0.0004
Time series SE	0.003	0.0001	0.0001	0.0001	0.002	0.0002	0.001
Minimum	0.813	−0.046	−0.054	−0.109	−0.890	0.007	0.019
2.5^th percentile	1.023	−0.020	−0.040	−0.057	−0.500	0.019	0.040
Q1	1.194	−0.005	−0.029	−0.029	−0.271	0.031	0.068
Medium (Q2)	1.302	0.003	−0.024	−0.015	−0.150	0.040	0.092
Q3	1.422	0.010	−0.018	−0.0003	−0.029	0.051	0.125
97.5^th percentile	1.697	0.021	−0.007	0.027	0.193	0.078	0.231
Maximum	2.324	0.032	0.006	0.082	0.511	0.143	0.658
Mode	1.250	0.003	−0.028	−0.015	−0.150	0.035	0.075
Variance	0.030	0.0001	0.0001	0.001	0.032	0.0002	0.002
Skewness	0.550	−0.361	0.082	−0.058	−0.027	0.957	1.656
Kurtosis	0.558	0.152	0.011	0.001	−0.009	1.510	4.992
95% credible interval	(1.023, 1.697)	−0.020, 0.021)	(−0.040, −0.007)	(−0.057, 0.027)	(−0.500, 0.193)	(0.019, 0.078)	(0.040, 0.231)
P (.>0|data)	1.000	0.598	0.003	0.244	0.199	1.000	1.000