Feature Screening via Mutual Information Learning Based on Nonparametric Density Estimation

Table 6

The proportions of and in Example 4.

Model	Parameter	cov (X)	Method
(a)			PC-SIS	1.00	0.95	0.68	0.64
			MV-SIS	1.00	0.99	0.86	0.86
			MI-SIS2	1.00	0.89	0.74	0.56
			MI-SIS	1.00	0.97	0.59	0.58
			PC-SIS	1.00	1.00	0.98	0.98
			MV-SIS	1.00	1.00	1.00	1.00
			MI-SIS2	1.00	1.00	0.96	0.96
			MI-SIS	1.00	1.00	1.00	1.00
(b)			PC-SIS	0.34	0.57	0.97	0.20
			MV-SIS	0.38	0.54	1.00	0.26
			MI-SIS2	0.46	0.65	0.98	0.28
			MI-SIS	0.98	1.00	0.95	0.92
			PC-SIS	0.84	0.81	0.90	0.56
			MV-SIS	0.41	0.46	0.97	0.24
			MI-SIS2	0.81	0.83	0.91	0.57
			MI-SIS	1.00	1.00	0.90	0.90