Skip to main content
Figure 4 | BMC Bioinformatics

Figure 4

From: Nonparametric relevance-shifted multiple testing procedures for the analysis of high-dimensional multivariate data with small sample sizes

Figure 4

Power for varying levels of sample sizes per group using 5,000 variables. As in Figure 3 the power for varying levels of samples sizes per group are presented. The simulation settings were the same using in Figure 3. Only the expected values of the 50 variables under H1 were set to 2.5 and 1/2.5 and results consisted of 1,000 simulation runs. The simulations carried out for the permutation algorithm were time consuming. Therefore, the power computed for sample size 10 per group was simulated using 100 runs and the number of permutations in each run was restricted to 100,000.

Back to article page