Development of New Robust Optimal Score Function for the Weibull Distributed Error Term in Multilevel Models

Table 10

Bias and MSE of using Weibull, Wilcoxon, and REML methods when  = 6..

		REML		Weibull		Wilcoxon		Precision
N2	N1	Bias	MSE	Bias	MSE	Bias	MSE	Weib/REML	Weib/Wil	Wil/REML
5	5	9.38	2.478	3.425	2.352	4.184	0.249	0.365	0.819	0.819
	10	9.608	2.632	4.753	2.417	4.695	0.037	0.495	1.012	1.012
	20	10.495	2.583	6.315	2.361	6.173	0.479	0.602	1.023	1.023
	40	16.952	2.645	12.214	2.432	11.902	0.4	0.721	1.026	1.026
10	5	4.841	2.801	2.716	2.553	2.643	1.009	0.561	1.028	1.028
	10	4.977	2.782	3.056	2.523	2.916	0.627	0.614	1.048	1.048
	20	7.656	2.841	6.01	2.576	5.813	1.566	0.785	1.034	1.034
	40	9.788	2.805	7.64	2.544	7.319	0.394	0.781	1.044	1.044
20	5	3.23	2.851	1.957	2.574	1.842	0.203	0.606	1.062	1.062
	10	3	2.799	2.203	2.524	2.087	0.057	0.734	1.055	1.055
	20	4.107	2.891	3.148	2.608	2.994	0.522	0.767	1.051	1.051
	40	5.178	2.842	4.182	2.551	3.934	1.604	0.808	1.063	1.063
40	5	2.199	2.869	1.518	2.594	1.427	0.894	0.691	1.064	1.064
	10	3.022	2.975	2.44	2.678	2.348	1.137	0.807	1.039	1.039
	20	2.871	2.87	2.24	2.57	2.129	0.36	0.78	1.052	1.052
	40	3.864	2.874	3.142	2.574	2.987	0.779	0.813	1.052	1.052