Optimizing the maximum reported cluster size for the multinomial-based spatial scan statistic

Moon, Jisu; Kim, Minseok; Jung, Inkyung

doi:10.1186/s12942-023-00353-4

International Journal of Health Geographics

Table 4 Multinomial model: simulation results for the true cluster model (B) and alternative hypothesis (3) using elliptical windows

From: Optimizing the maximum reported cluster size for the multinomial-based spatial scan statistic

		Maximum reported cluster size (MRCS)																		Default setting
		1%	2%	3%	4%	5%	6%	8%	10%	12%	15%	20%	25%	30%	35%	40%	45%	50%	Overall	Default setting
SCIC₁	Freq^a	0	1	4	10	46	52	424	117	74	44	27	9	2	4	1	3	1	819	819
	Sen^b	NA	0.200	0.250	0.380	0.552	0.650	0.881	0.916	0.924	0.973	0.874	0.911	1.000	0.750	0.400	0.733	0.800	0.850	0.868
	PPV^c	NA	1.000	0.750	0.917	0.889	0.911	0.954	0.756	0.620	0.532	0.336	0.270	0.278	0.173	0.080	0.094	0.105	0.827	0.755
	Mis^d	NA	0.058	0.062	0.048	0.039	0.031	0.012	0.029	0.050	0.068	0.145	0.193	0.188	0.279	0.377	0.531	0.507	0.036	0.055
SCIC₂	Freq	0	1	4	13	46	52	416	112	73	41	28	11	4	6	5	6	1	819	819
	Sen	NA	0.200	0.250	0.523	0.578	0.654	0.878	0.913	0.921	0.976	0.857	0.909	1.000	0.833	0.880	0.833	0.800	0.850	0.868
	PPV	NA	1.000	0.750	0.946	0.903	0.900	0.951	0.754	0.618	0.533	0.322	0.251	0.236	0.161	0.140	0.112	0.105	0.814	0.755
	Mis	NA	0.058	0.062	0.037	0.036	0.031	0.013	0.030	0.051	0.068	0.152	0.212	0.246	0.341	0.394	0.493	0.507	0.042	0.055
Elbow	Freq	0	1	5	18	56	57	429	105	73	33	21	11	2	3	3	2	0	819	819
	Sen	NA	0.200	0.320	0.611	0.632	0.653	0.882	0.897	0.915	0.964	0.800	0.964	1.000	0.667	0.800	0.600	NA	0.844	0.868
	PPV	NA	1.000	0.800	0.961	0.899	0.891	0.949	0.738	0.609	0.513	0.295	0.262	0.225	0.118	0.113	0.094	NA	0.830	0.755
	Mis	NA	0.058	0.055	0.030	0.033	0.032	0.013	0.032	0.053	0.074	0.163	0.208	0.268	0.372	0.473	0.449	NA	0.036	0.055
MCS-P	Freq	0	3	5	13	50	56	384	104	80	53	41	14	7	5	2	2	0	819	819
	Sen	NA	0.133	0.160	0.492	0.616	0.632	0.874	0.919	0.940	0.962	0.927	0.957	0.971	0.800	0.700	0.600	NA	0.850	0.868
	PPV	NA	0.667	0.400	0.808	0.844	0.879	0.955	0.774	0.650	0.545	0.400	0.317	0.253	0.180	0.133	0.094	NA	0.804	0.755
	Mis	NA	0.068	0.078	0.046	0.036	0.034	0.012	0.025	0.042	0.063	0.108	0.153	0.211	0.278	0.348	0.449	NA	0.037	0.055
MCHS-P	Freq	0	1	3	11	47	54	381	107	81	54	46	17	7	5	3	2	0	819	819
	Sen	NA	0.200	0.267	0.655	0.647	0.644	0.873	0.920	0.936	0.967	0.904	0.953	0.971	0.800	0.800	0.600	NA	0.861	0.868
	PPV	NA	1.000	0.667	0.982	0.888	0.895	0.950	0.762	0.645	0.536	0.375	0.303	0.253	0.180	0.144	0.094	NA	0.799	0.755
	Mis	NA	0.058	0.063	0.026	0.033	0.032	0.013	0.027	0.044	0.066	0.124	0.166	0.211	0.278	0.353	0.449	NA	0.039	0.055

^aFreq: frequency
^bSen: sensitivity
^cPPV: positive predictive value
^dMis: misclassification
Sensitivity, PPV, and misclassification rate at the most frequently selected optimal MRCS are shown in bold

Back to article page

ISSN: 1476-072X

Contact us

Submission enquiries: journalsubmissions@springernature.com