Skip to main content

Table 2 Summary of statistical power to significantly detect differential methylation between cases and controls

From: Guidance for DNA methylation studies: statistical insights from the Illumina EPIC array

Sample Size

Standard Deviation

0.01

0.03

0.05

0.07

0.09

0.15

Mean Difference = 2%

 100

100%

1.26%

0.03%

0.00%

0.00%

0.00%

 200

100%

21.4%

0.45%

0.04%

0.01%

0.00%

 500

100%

97.8%

17.6%

1.43%

0.19%

0.01%

 1000

100%

100%

82.7%

19.7%

3.22%

0.06%

Mean Difference = 5%

 100

100%

99.1%

24.4%

2.18%

0.29%

0.01%

 200

100%

100%

93.0%

32.0%

6.07%

0.11%

 500

100%

100%

100%

99.4%

78.4%

4.81%

 1000

100%

100%

100%

100%

100%

45.8%

  1. Presented are example power calculations for a range of scenarios, varying effect size, sample size and variance for a binary phenotype. Power calculations are for a two-sided, two-sample t-test with a significance threshold of P < 9.42 × 10− 8. The sample size is the total number of samples with a 50:50 split between groups