A simulation study for evaluating the performance of clustering measures in multilevel logistic regression

Adam, Nicholas Siame; Twabi, Halima S.; Manda, Samuel O.M.

doi:10.1186/s12874-021-01417-4

BMC Medical Research Methodology

Table 3 Average root mean square errors for the estimated fixed effects, cluster effect, ICC, MOR, IOR-80 and SOI at cluster variances of 1.0 and 1.5

From: A simulation study for evaluating the performance of clustering measures in multilevel logistic regression

Clusters	Cluster	β₀	β₁	β₂	α	ICC	MOR	SOI	IOR-80	IOR-80
	Size								Lower	Upper
\(\mathbf {\sigma ^{2}_{u}=1.0}\)
10	5	0.062	0.008	0.009	0.010	0.028	0.217	0.011	0.012	0.870
	20	0.120	0.001	0.012	0.202	0.007	0.050	0.056	0.021	0.855
	50	0.042	0.041	0.001	0.024	0.012	0.079	0.017	0.007	0.086
	100	0.094	0.017	0.020	0.167	0.011	0.076	0.040	0.022	0.479
	250	0.002	0.009	0.008	0.096	0.005	0.034	0.031	0.009	0.424
50	5	0.023	0.009	0.002	0.015	0.020	0.135	0.012	0.012	0.478
	20	0.037	0.009	0.003	0.068	0.012	0.081	0.022	0.001	0.531
	50	0.025	0.006	0.001	0.006	0.005	0.036	0.008	0.002	0.117
	100	0.003	0.006	0.000	0.014	0.005	0.036	0.013	0.004	0.001
	250	0.006	0.006	0.005	0.024	0.006	0.039	0.010	0.001	0.228
100	5	0.004	0.004	0.024	0.032	0.012	0.082	0.008	0.012	0.109
	20	0.021	0.006	0.000	0.005	0.005	0.035	0.005	0.003	0.069
	50	0.013	0.006	0.001	0.032	0.003	0.017	0.010	0.003	0.168
	100	0.021	0.005	0.007	0.031	0.005	0.034	0.009	0.005	0.064
	250	0.004	0.010	0.003	0.018	0.003	0.018	0.007	0.001	0.104
300	5	0.014	0.024	0.012	0.038	0.023	0.151	0.017	0.010	0.627
	20	0.009	0.005	0.006	0.003	0.003	0.020	0.004	0.002	0.035
	50	0.005	0.002	0.008	0.010	0.002	0.015	0.009	0.001	0.069
	100	0.021	0.004	0.003	0.026	0.002	0.015	0.009	0.002	0.168
	250	0.009	0.003	0.001	0.013	0.002	0.015	0.009	0.002	0.069
500	5	0.007	0.033	0.004	0.017	0.025	0.165	0.004	0.019	0.058
	20	0.007	0.006	0.004	0.025	0.005	0.033	0.006	0.006	0.004
	50	0.003	0.001	0.002	0.007	0.002	0.010	0.002	0.001	0.003
	100	0.006	0.006	0.006	0.013	0.003	0.023	0.003	0.002	0.001
	250	0.012	0.004	0.001	0.015	0.002	0.011	0.007	0.001	0.001
\(\mathbf {\sigma ^{2}_{u}=1.5}\)
10	5	0.063	0.021	0.035	0.076	0.014	0.124	0.017	0.011	0.394
	20	0.005	0.016	0.028	0.140	0.013	0.120	0.030	0.014	0.459
	50	0.002	0.030	0.006	0.171	0.010	0.091	0.039	0.016	0.429
	100	0.002	0.014	0.002	0.014	0.010	0.085	0.010	0.003	0.360
	250	0.065	0.016	0.004	0.134	0.019	0.162	0.033	0.015	0.130
50	5	0.007	0.013	0.007	0.025	0.041	0.334	0.014	0.016	0.381
	20	0.038	0.015	0.001	0.050	0.013	0.112	0.010	0.008	0.045
	50	0.026	0.003	0.007	0.066	0.003	0.069	0.015	0.010	0.177
	100	0.056	0.003	0.007	0.069	0.008	0.069	0.016	0.007	0.144
	250	0.084	0.005	0.002	0.040	0.009	0.080	0.015	0.007	0.012
100	5	0.012	0.045	0.016	0.032	0.027	0.227	0.008	0.015	0.669
	20	0.040	0.009	0.005	0.047	0.007	0.059	0.011	0.006	0.247
	50	0.027	0.011	0.008	0.052	0.006	0.049	0.011	0.006	0.178
	100	0.069	0.001	0.006	0.069	0.004	0.031	0.016	0.006	0.139
	250	0.010	0.002	0.005	0.066	0.003	0.051	0.015	0.006	0.038
300	5	0.021	0.003	0.012	0.034	0.003	0.131	0.007	0.010	0.291
	20	0.021	0.000	0.006	0.026	0.003	0.016	0.007	0.002	0.214
	50	0.018	0.005	0.003	0.012	0.003	0.015	0.003	0.000	0.121
	100	0.013	0.003	0.001	0.014	0.003	0.046	0.004	0.001	0.123
	250	0.009	0.003	0.001	0.013	0.003	0.115	0.009	0.007	0.360
500	5	0.007	0.005	0.001	0.009	0.003	0.178	0.006	0.008	0.040
	20	0.001	0.005	0.000	0.028	0.003	0.039	0.007	0.000	0.035
	50	0.016	0.000	0.003	0.001	0.003	0.024	0.006	0.001	0.040
	100	0.029	0.001	0.001	0.028	0.003	0.013	0.007	0.002	0.019
	250	0.010	0.003	0.072	0.072	0.003	0.060	0.016	0.002	0.011

Back to article page

ISSN: 1471-2288

Contact us

General enquiries: journalsubmissions@springernature.com