Table 2.

Simulation results of estimating the cdf under nonstable disease incidence(θ = 0.5). EMP represents the empirical distribution estimate, PH represents the proposed semiparametric estimator based on proportional hazards model. AFT represents the proposed estimator based on accelerated failure time model. Bias represents the empirical bias, SSE represents the sampling standard error, and CI.L and CI.U represent the averaged lower and upper limits of 95% confidence intervals, respectively.

Estimator\z		0.2	0.4	0.6	0.8
(a) n = 200
EMP	Bias	−0.053	−0.079	−0.078	−0.051
PH	Bias	−0.001	0.001	0.003	0.001
	SSE	0.082	0.081	0.065	0.040
	CI.L	0.101	0.278	0.491	0.722
	CI.U	0.347	0.557	0.724	0.874
AFT	Bias	−0.020	−0.025	−0.021	−0.012
	SSE	0.031	0.039	0.038	0.029
	CI.L	0.118	0.297	0.503	0.730
	CI.U	0.242	0.453	0.655	0.846
(b) n = 400
EMP	Bias	−0.054	−0.080	−0.078	−0.052
PH	Bias	0.000	0.000	−0.001	−0.001
	SSE	0.058	0.056	0.043	0.028
	CI.L	0.122	0.308	0.518	0.745
	CI.U	0.316	0.518	0.690	0.853
AFT	Bias	−0.019	−0.023	−0.019	−0.010
	SSE	0.022	0.027	0.026	0.021
	CI.L	0.137	0.323	0.529	0.748
	CI.U	0.225	0.431	0.633	0.832