Table 5.

Results of Simulation Study 1 to assess performance of ICC estimation methods when data follow a common correlation model, with same (ρ, π) for all clusters using 2000 simulated data sets

A. Bias and mean estimated values
True ρ	True π	Estimated mean bias				Estimated mean relative bias				Mean ρ̂
		ano	fc	pe	gee	ano	fc	pe	gee	ano	fc	pe	gee	re
0.02	0.1	−0.001	−0.003	−0.004	−0.005	−0.05	−0.15	−0.20	−0.25	0.019	0.017	0.016	0.015	0.056
	0.2	−0.001	−0.003	−0.003	−0.004	−0.05	−0.15	−0.15	−0.20	0.019	0.017	0.017	0.016	0.033
	0.3	−0.001	−0.003	−0.003	−0.004	−0.05	−0.15	−0.15	−0.20	0.019	0.017	0.017	0.016	0.025
	0.4	0.000	−0.002	−0.002	−0.004	0.00	−0.10	−0.10	−0.20	0.020	0.018	0.018	0.016	0.023
	0.5	0.000	−0.002	−0.002	−0.004	0.00	−0.10	−0.10	−0.20	0.020	0.018	0.018	0.016	0.022
0.05	0.1	−0.002	−0.004	−0.005	−0.008	−0.04	−0.08	−0.10	−0.16	0.048	0.046	0.045	0.042	0.125
	0.2	−0.001	−0.003	−0.003	−0.006	−0.02	−0.06	−0.06	−0.12	0.049	0.047	0.047	0.044	0.079
	0.3	−0.001	−0.003	−0.003	−0.005	−0.02	−0.06	−0.06	−0.10	0.049	0.047	0.047	0.045	0.063
	0.4	0.000	−0.002	−0.002	−0.005	0.00	−0.04	−0.04	−0.10	0.050	0.048	0.048	0.045	0.057
	0.5	0.000	−0.002	−0.002	−0.004	0.00	−0.04	−0.04	−0.08	0.050	0.048	0.048	0.046	0.055
0.10	0.1	−0.003	−0.006	−0.007	−0.011	−0.03	−0.06	−0.07	−0.11	0.097	0.094	0.093	0.089	0.234
	0.2	−0.002	−0.005	−0.005	−0.008	−0.02	−0.05	−0.05	−0.08	0.098	0.095	0.095	0.092	0.159
	0.3	−0.001	−0.004	−0.004	−0.007	−0.01	−0.04	−0.04	−0.07	0.099	0.096	0.096	0.093	0.132
	0.4	0.000	−0.003	−0.003	−0.005	0.00	−0.03	−0.03	−0.05	0.100	0.097	0.097	0.095	0.121
	0.5	0.001	−0.002	−0.002	−0.005	0.01	−0.02	−0.02	−0.05	0.101	0.098	0.098	0.095	0.118
0.25	0.1	−0.009	−0.013	−0.016	−0.026	−0.04	−0.05	−0.06	−0.10	0.241	0.237	0.234	0.224	0.510
	0.2	−0.004	−0.008	−0.009	−0.014	−0.02	−0.03	−0.04	−0.06	0.246	0.242	0.241	0.236	0.393
	0.3	−0.001	−0.005	−0.006	−0.010	0.00	−0.02	−0.02	−0.04	0.249	0.245	0.244	0.240	0.350
	0.4	0.001	−0.004	−0.005	−0.008	0.00	−0.02	−0.02	−0.03	0.251	0.246	0.245	0.242	0.329
	0.5	0.001	−0.004	−0.004	−0.008	0.00	−0.02	−0.02	−0.03	0.251	0.246	0.246	0.242	0.324

B. Empirical coverage probability of 95% confidence intervals for ρ
True ρ	True π	Wald interval ECP			Linear interval ECP
		ano	fc	pe	ano	fc	pe	gee
0.02	0.1	1.000	1.000	1.000	0.718	0.666	0.654	0.871
	0.2	0.999	0.998	0.998	0.754	0.711	0.705	0.858
	0.3	0.997	0.996	0.996	0.790	0.754	0.722	0.858
	0.4	0.990	0.991	0.994	0.834	0.796	0.777	0.860
	0.5	0.987	0.991	0.993	0.839	0.812	0.786	0.869
0.05	0.1	1.000	1.000	1.000	0.876	0.842	0.852	0.797
	0.2	1.000	1.000	1.000	0.910	0.884	0.878	0.835
	0.3	0.999	0.999	0.998	0.915	0.887	0.884	0.858
	0.4	0.996	0.995	0.996	0.926	0.909	0.902	0.865
	0.5	0.992	0.993	0.996	0.922	0.905	0.900	0.872
0.10	0.1	1.000	1.000	1.000	0.963	0.949	0.953	0.793
	0.2	0.999	0.999	0.998	0.976	0.965	0.965	0.839
	0.3	0.999	0.999	0.998	0.976	0.962	0.965	0.860
	0.4	0.995	0.996	0.997	0.969	0.955	0.956	0.873
	0.5	0.996	0.996	0.997	0.968	0.952	0.958	0.879
0.25	0.1	1.000	0.998	0.998	0.994	0.989	0.992	0.872
	0.2	0.999	0.998	0.998	0.997	0.991	0.994	0.867
	0.3	0.998	0.998	0.998	0.994	0.988	0.991	0.882
	0.4	0.996	0.996	0.996	0.988	0.980	0.988	0.898
	0.5	0.992	0.992	0.994	0.984	0.978	0.982	0.898

ECP, empirical coverage probability; ano, ANOVA; fc, Fleiss-Cusick; pe, Pearson; gee, generalized estimating equations; re, random intercept logistic regression