Power and false-positive rates for the restricted partition method (RPM) in a large candidate gene data set

BMC Proceedings

Table 2 Power and false positive rates - unrelated subjects (N = 1130)

CAC	p-value Threshold					R² Threshold					R² Mean^a
	10^-3	10^-4	10^-5	10^-6	10^-7	0.005	0.01	0.02	0.03	0.04
Univariate
Power^b
Het	100	100	100	100	97	100	100	100	95	68	0.0447
ME1	0	0	0	0	0	9	0	0	0	0	0.0011
ME2	2	0	0	0	0	22	5	0	0	0	0.0027
PE1	0	0	0	0	0	6	0	0	0	0	0.0007
PE2	0	0	0	0	0	1	0	0	0	0	0.0002
Avg(#FP)^c	49.0	7.5	1.3	0.1	0.03	757.4	89.2	2.3	1.0	0.6
E(#FP)	41.1	4.1	0.4	0.0	0.0
Two-way
Power
ME1*ME2	100	100	100	100	100	100	100	100	100	100	0.0806
PE1*PE2	100	100	100	100	100	100	100	100	100	100	0.1187
Avg(#FP)	1.8 M	400 K	3634	1183	422	120 M	24 M	513 K	13.3 K	550
E(#FP)	845 K	84 K	8446	845	84.5
Univariate
Coronary Event
Power
Het	4	2	0	0	0	44	15	2	0	0	0.0041
ME1	0	0	0	0	0	4	0	0	0	0	0.0007
ME2	1	0	0	0	0	4	1	0	0	0	0.0010
PE1	0	0	0	0	0	1	0	0	0	0	0.0003
PE2	0	0	0	0	0	4	0	0	0	0	0.0006
Smoke	24	12	4	2	1	63	25	4	1	0	0.0068
SLoc	0	0	0	0	0	8	1	0	0	0	0.0012
Event Loc	0	0	0	0	0	18	1	0	0	0	0.0017
Avg(#FP)	36.7	4.5	0.8	0.1	0.01	631.1	69.0	1.8	0.1	0.0
E(#FP)	41.1	4.1	0.4	0.0	0.0
Two-way
Power
ME1*ME2	43	16	7	1	0	98	88	43	6	0	0.0183
PE1*PE2	94	75	45	25	8	100	100	92	51	9	0.0301
Smoke*SLoc	25	7	4	1	0	81	54	12	3	0	0.0114
Avg(#FP)	746 K	83 K	9740	342	84	100 M	18 M	402 K	15.6 K	967
E(#FP)	845 K	84 K	8446	845	84.5

^aMean RPM R² for the factors in the model estimated by the RPM in 100 data replicates
^bPower, number of replicates for which the factor passed the threshold
^cAvg(#FP), average number of observed "false positives" in the univariate analyses per replicate. For two-way analyses, estimated from 10⁸ sampled pairs for the analyses of R² and 10⁷ sampled pairs for the analyses of p-values.
^dE(#FP), expected number of false positives in the analysis of one replicate assuming the tests were independent.

ISSN: 1753-6561