Table 1.

Power calculation under Scenario (A)

Strategy	Corr	MAF	Method
			LR	FPM	TPM	Lasso	Enet	GRLR
I	0.0	0.10	0.196	0.206	0.198	0.210	0.226	0.196
		0.30	0.638	0.620	0.602	0.688	0.670	0.650
		0.50	0.792	0.734	0.730	0.790	0.828	0.826
	0.2	0.10	0.184	0.216	0.194	0.194	0.204	0.206
		0.30	0.712	0.642	0.622	0.690	0.726	0.704
		0.50	0.860	0.794	0.788	0.902	0.888	0.870
II	0.0	0.10	0.008	0.078	0.070	0.032	0.052	0.124
		0.30	0.122	0.266	0.252	0.340	0.392	0.558
		0.50	0.354	0.304	0.306	0.526	0.624	0.768
	0.2	0.10	0.018	0.088	0.064	0.066	0.078	0.126
		0.30	0.202	0.296	0.300	0.364	0.458	0.608
		0.50	0.400	0.370	0.360	0.628	0.690	0.806

Results of power simulations for six methods under Scenario (A) (two causal SNPs). Two definitions of testing success, Strategy I (requiring that at least one of the two SNPs is significant) and Strategy II (requiring significance at both SNPs), are applied in comparisons; The number of replication runs is 500 for all the simulations. Corr = correlation coefficient; MAF = minor allele frequency.