I have a list of p-values and I would like to calculate the adjust p-values for multiple comparisons for the FDR. In R, I can use:
pval <- read.csv(\"my_f
Here is an in-house function I use:
def correct_pvalues_for_multiple_testing(pvalues, correction_type = "Benjamini-Hochberg"):
"""
consistent with R - print correct_pvalues_for_multiple_testing([0.0, 0.01, 0.029, 0.03, 0.031, 0.05, 0.069, 0.07, 0.071, 0.09, 0.1])
"""
from numpy import array, empty
pvalues = array(pvalues)
n = float(pvalues.shape[0])
new_pvalues = empty(n)
if correction_type == "Bonferroni":
new_pvalues = n * pvalues
elif correction_type == "Bonferroni-Holm":
values = [ (pvalue, i) for i, pvalue in enumerate(pvalues) ]
values.sort()
for rank, vals in enumerate(values):
pvalue, i = vals
new_pvalues[i] = (n-rank) * pvalue
elif correction_type == "Benjamini-Hochberg":
values = [ (pvalue, i) for i, pvalue in enumerate(pvalues) ]
values.sort()
values.reverse()
new_values = []
for i, vals in enumerate(values):
rank = n - i
pvalue, index = vals
new_values.append((n/rank) * pvalue)
for i in xrange(0, int(n)-1):
if new_values[i] < new_values[i+1]:
new_values[i+1] = new_values[i]
for i, vals in enumerate(values):
pvalue, index = vals
new_pvalues[index] = new_values[i]
return new_pvalues