Skip to main content
Figure 4 | BMC Genetics

Figure 4

From: Properties of permutation-based gene tests and controlling type 1 error using a summary statistic based gene test

Figure 4

Power comparison for a Hotelling’s T2 approach versus summary statistic test as a function of effect size. Power comparison of Moskvina et al.’s method (solid, black line) with our summary statistic based method (dashed, blue line) when the causal SNP is in a block of high LD. This graph looks identical to that when the causal SNP is not in a block of high LD because the power for both methods is not a function of the correlation of the SNPs and where causal SNPs are located relative to regions of correlation. Q-Q plot of permutation-based gene test statistic under alternative for correlated region versus uncorrelated region.

Back to article page