Table I.

The bias for the estiamte results for SSRS, d = 0.3.

θ	t	Bias1*	Bias2*	Bias(JK1)	Bias(JK2)	RMSE1	RMSE2
0.95	960	−0.0015	−0.0033	1.0205	1.0205	0.0146	0.0150
	480	−0.0039	−0.0071	1.0347	1.0347	0.0206	0.0214
	240	−0.0071	−0.0129	1.0608	1.0606	0.0304	0.0324
0.9	960	0.0010	0.0019	1.0135	1.0089	0.0224	0.0224
	480	−0.0039	−0.0056	0.9847	0.9877	0.0328	0.0331
	240	−0.0063	−0.0096	1.0658	1.0655	0.0460	0.0468
0.8	960	−0.0016	−0.0014	1.0251	1.0282	0.0319	0.0319
	480	−0.0039	−0.0065	1.0128	1.0128	0.0470	0.0474
	240	0.0073	0.0100	1.0369	1.0367	0.0682	0.0688
0.7	960	−0.0003	0.0008	1.0347	1.0347	0.0375	0.0375
	480	−0.0026	0.0030	1.0350	1.0349	0.0544	0.0545
	240	0.0055	0.0084	1.0806	1.0802	0.0771	0.0777
0.6	960	0.0025	0.0031	1.0218	1.0218	0.0413	0.0414
	480	0.0044	0.0046	1.0847	1.0863	0.0557	0.0558
	240	0.0097	0.0123	1.2465	1.2468	0.0717	0.0724
0.55	960	0.0028	0.0034	1.1927	1.1927	0.0359	0.0360
	480	0.0054	0.0088	1.3268	1.3260	0.0459	0.0465
	240	0.0109	0.0142	1.4992	1.4983	0.0599	0.0609

Note:

^*1 = unweighted estimator, 2 = weighted estimator.

$\text{Bias}1=\widehat{\theta }1-\theta$, $\text{Bias}2=\widehat{\theta }2-\theta$, Bias(JK1)=SE(JK1)/SE(EMP1), Bias(JK2)=SE(JK2)/SE(EMP2), SE = standard error, JK = jackknife variance estimate, EMP = empirical variance estimate, RMSE = root of mean squared error.