Table 5.

SCAD for logistic regression models based on case-control data with $n_1$ cases and $n_0$ controls

$F_{\mathbf{X}}$	n	${\mathit{\beta }}^{\ast }$	FP rate	FN rate	Coverage of zero for				Coverage of 95 % CIs of ${\mathit{\beta }}^{\ast }$ for $\widehat{\mathit{\beta }}\ne 0$
					$\mathit{\beta }=0$		${\mathit{\beta }}^{\ast }\ne 0$
					(Adapt${}^{\mathrm{a}}$)	(Oracle${}^{\mathrm{b}}$)	(Adapt)	(Oracle)	(Adapt)	(Oracle)
Normal	100	0.25	0.002	0.995	0.999	0.998	0.996	0.995	0.004	0.001
Normal	200	0.25	0.003	0.992	0.998	0.997	0.992	0.992	0.005	0.002
Normal	500	0.25	0.004	0.979	0.997	0.997	0.980	0.979	0.015	0.013
Normal	100	0.500	0.002	0.986	0.999	0.998	0.989	0.985	0.014	0.007
Normal	200	0.500	0.007	0.938	0.995	0.994	0.937	0.933	0.061	0.047
Normal	500	0.500	0.052	0.526	0.971	0.968	0.525	0.514	0.503	0.495
Normal	100	1.000	0.005	0.905	0.999	0.996	0.937	0.899	0.104	0.093
Normal	200	1.000	0.031	0.422	0.982	0.977	0.399	0.377	0.624	0.610
Normal	500	1.000	0.024	0.137	0.987	0.986	0.055	0.051	0.924	0.925
Binomial	100	0.25	0.002	0.984	0.999	0.999	0.996	0.994	0.006	0.003
Binomial	200	0.25	0.002	0.977	0.999	0.999	0.985	0.982	0.015	0.011
Binomial	500	0.25	0.005	0.858	0.996	0.995	0.884	0.867	0.119	0.112
Binomial	100	0.500	0.002	0.945	0.999	0.998	0.979	0.965	0.037	0.029
Binomial	200	0.500	0.015	0.732	0.992	0.990	0.778	0.751	0.249	0.231
Binomial	500	0.500	0.018	0.148	0.987	0.983	0.133	0.110	0.850	0.857
Binomial	100	1.000	0.004	0.796	0.999	0.998	0.891	0.823	0.135	0.169
Binomial	200	1.000	0.020	0.126	0.987	0.982	0.103	0.091	0.870	0.862
Binomial	500	1.000	0.014	0.057	0.990	0.988	0.004	0.003	0.940	0.937

$F_X$ is the distribution of the predictors $\mathbf{X}$

FP false positive, FN false negative

${}^{\mathrm{a}}$ Corresponds to Algorithm 1, and ${}^{\mathrm{b}}$ to Algorithm 2 in the text