Permutation-based variance component test in generalized linear mixed model with application to multilocus genetic association study

Table 2 Estimated powers for Simulation 1 with the random effects variance component equal to 0.15 and 0.20 and varying number of random effects

n	Method	Kwithτ² = 0.15			Kwithτ² = 0.20
n	Method	20	30	40	20	30	40
400	Permutation	0.296	0.380	0.433	0.506	0.577	0.704
	Score	0.276	0.363	0.402	0.501	0.557	0.689
	Mixture (0.50)	0.158	0.235	0.282	0.349	0.441	0.567
	Mixture (0.65)	0.187	0.269	0.318	0.393	0.476	0.615
600	Permutation	0.436	0.566	0.630	0.712	0.837	0.878
	Score	0.430	0.548	0.604	0.704	0.816	0.868
	Mixture (0.50)	0.255	0.382	0.463	0.538	0.686	0.794
	Mixture (0.65)	0.292	0.437	0.501	0.589	0.717	0.826
800	Permutation	0.559	0.704	0.777	0.840	0.922	0.951
	Score	0.557	0.702	0.771	0.830	0.917	0.948
	Mixture (0.50)	0.380	0.526	0.642	0.727	0.851	0.905
	Mixture (0.65)	0.427	0.573	0.682	0.765	0.873	0.922
1000	Permutation	0.688	0.792	0.865	0.913	0.950	0.987
	Score	0.679	0.787	0.864	0.909	0.949	0.983
	Mixture (0.50)	0.517	0.637	0.774	0.828	0.914	0.966
	Mixture (0.65)	0.562	0.677	0.801	0.852	0.926	0.970

Note: Permutation is the proposed permutation-based LRT, Score is the score-based sequence kernel association test given in Wu, et al. [31] that was originally developed in Lin (1997), Mixture (0.50) and Mixture (0.65) respectively correspond to the asymptotic 0.50:0.50 and 0.65:035 mixtures of chi-square distributions. Here K is the number of random effects, i.e., the number of SNPs included in a gene, and τ² is the random effects variance component.

ISSN: 1471-2288