Several methods of combining P-values
Project description
HCtest -- Higher Criticism Test
Higher Criticism (HC) test statistics for testing the global significance of many independent hypotheses. As an input, the test receives a list of P-values and returns the HC test statistics. See (Donoho & Jin 2004)
Example:
from scipy.stats import norm
from multitest import MultiTest
n = 1000 #number of samples
X = norm.rvs(size=n)
pvals = norm.sf(X)
mt = MultiTest(pvals)
hc_val, p_th = mt.HCstar(gamma = 0.25)
minus_log_min_pval = mt.minp()
fdr, pval_fdr = mt.fdr()
print(f"Higher-Criticism test statistic = {hc_val}")
print(f"False-discovery rate {q} critical P-value = {pval_fdr}")
print(f"Bonferroni {minus_log_min_pval}")
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Close
Hashes for multiple-hypothesis-testing-0.1.0.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5812e9383777d43847cf360897ffc641a2ede024c21ab149929396df0815dd38 |
|
MD5 | f209665969206272a4bc0d9cb7239681 |
|
BLAKE2b-256 | 3eaaff6358accbd81f73c1bfcb292ba61187028902b6351423d544318b7e977c |
Close
Hashes for multiple_hypothesis_testing-0.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | ea00367d5d47dc89ca14c250c0350f436d03627cc21024d91e8113690ef5536c |
|
MD5 | 136eccc5e56caf19bdd48570a96ec949 |
|
BLAKE2b-256 | 38b4b6e3f259ec061499df9571ecf69773b5e7a27df955f08673081078aa3a80 |