Skip to main content

Table 2 Empirical size for each method at significance level 0.05 with 10 4 replicates from the simulation study

From: Detecting differentially methylated loci for multiple treatments based on high-throughput methylation data

Simulation setting (3 treatments)

Combined ANOVA

Combined K-W

New

Distribution

Sample size

Parameters

Uniform U(a,b)

(20,20,20)

a = (0,0,0), b = (1,1,1)

0.051

0.045

0.047

a = (0,0,0), b = (0.5,0.5,0.5)

0.051

0.045

0.045

a = (0.5,0.5,0.5), b = (1,1,1)

0.055

0.046

0.047

(15,20,25)

a = (0,0,0), b = (1,1,1)

0.052

0.043

0.046

a = (0,0,0), b = (0.5,0.5,0.5)

0.052

0.044

0.050

a = (0.5,0.5,0.5), b = (1,1,1)

0.049

0.040

0.043

Truncated Normal TN (μ ,σ2)

(20,20,20)

μ= (0.5,0.5,0.5),

σ = (1,1,1)/5

0.050

0.043

0.048

μ= (0.5,0.5,0.5),

σ = (1,2,3)/5

0.058

0.050

0.045

μ= (0.2,0.2,0.2),

σ = (1,1,1)/5

0.049

0.050

0.043

μ= (0.8, 0.8, 0.8),

σ = (1,1,1)/5

0.046

0.043

0.048

(15,20,25)

μ= (0.5,0.5,0.5),

σ = (1,1,1)/5

0.050

0.046

0.045

μ= (0.5,0.5,0.5),

σ = (1,1.2,1.3)/5

0.053

0.041

0.033

μ= (0.2,0.2,0.2),

σ = (1,1,1)/5

0.050

0.046

0.051

μ= (0.8, 0.8, 0.8),

σ = (1,1,1)/5

0.049

0.044

0.048

Beta (c,d)

(20,20,20)

c = (1,1,1), d = (1,1,1)

0.050

0.044

0.049

c = (1,1,1), d = (5,5,5)

0.046

0.045

0.043

c = (5,5,5), d = (1,1,1)

0.048

0.044

0.045

c = (5,5,5), d = (5,5,5)

0.049

0.041

0.044

(15,20,25)

c = (1,1,1), d = (1,1,1)

0.049

0.044

0.046

c = (1,1,1), d = (5,5,5)

0.045

0.042

0.047

c = (5,5,5), d = (1,1,1)

0.049

0.049

0.048

c = (5,5,5), d = (5,5,5)

0.052

0.044

0.052