Skip to main content

Table 2 Percentiles for absolute difference between asymptotic power and simulation power

From: Power and sample size calculations in the presence of phenotype errors for case/control genetic association studies

  5% significance level 1% significance level
  Di-allelic locus  
Minimum 0.0000 0.0000
10th percentile 0.0002 0.0002
25th percentile 0.0005 0.0004
50th percentile 0.0010 0.0011
75th percentile 0.0028 0.0026
90th percentile 0.0065 0.0057
Maximum 0.0099 0.0119
  Tetra-allelic locus  
Minimum 0.0000 0.0000
10th percentile 0.0000 0.0000
25th percentile 0.0007 0.0008
50th percentile 0.0012 0.0014
75th percentile 0.0028 0.0032
90th percentile 0.0072 0.0081
Maximum 0.0102 0.0111
  1. Power simulations are performed at 100,000 iterations for each set of parameter specifications in the Methods section. Here we report various percentiles of the absolute difference |simulation power - asymptotic power| for our simulations. For each locus type (di-allelic, tetra-allelic), percentiles are computed using 27 = 128 settings documented in table 1.