Table 4.

The Power of the Single-Marker Test, Hotelling's T² Test, and the Collapsing Method when Noncausal Rare Variants Are Included and Causal Rare Variants Are Excluded

	Total Variant Frequency
	0.05a			0.01b
No. Included	S	H	C	S	H	C
0	0.05	0.40	0.86	0.05	0.39	0.83
5	0.04	0.30	0.70	0.04	0.29	0.68
10	0.03	0.23	0.55	0.03	0.23	0.55
20	0.03	0.16	0.33	0.02	0.15	0.36
No. Excluded	S	H	C	S	H	C
2	0.05	0.31	0.72	0.05	0.30	0.69
4	0.05	0.21	0.52	0.04	0.20	0.50
6	0.04	0.12	0.28	0.04	0.12	0.27
8	0.03	0.05	0.08	0.03	0.05	0.08

The effect of including noncausal variants and excluding causal variants on the power of the single-marker test (S), Hotelling's T² test (H), and the collapsing method (C) when there are ten rare causal variants in a gene, with a total variant frequency of either 0.05 or 0.01. In the upper section of the table, also included in the analysis are 5, 10, and 20 rare noncausal variants, with the same allele frequencies as the causal variants. In the lower section of the table, 2, 4, 6, and 8 causal variants are excluded from the analysis.

^aSample size of 250 cases and 250 controls.

^bSample size of 1000 cases and 1000 controls.