Skip to main content

TwoSamplesBinomial: Two-sample testing for counts data

Usually in the context of a multiple testing approach to compare two or more frequency tables. Combine with multiple-hypothesis-testing to obtain a global test for the significance of the difference between the tables.

References:

  • [1] D. L. Donoho and A. Kipnis. (2022) Higher criticism to compare two large frequency tables, with sensitivity to possible rare and weak differences. Annals of Statistics.
  • [2] C. B. Dean. (1992) Testing for Overdispersion in Poisson and Binomial Regression Models. Journal of the American Statistical Association

Methods:

  • bin_allocation_test (the test from [1])
  • bin_variance_test (test from [2])
  • bin_variance_test_df the same as bin_variance_test plus additional information

Additional auxiliary function of independent interest:

  • poisson_test Vectorized one-sided Poisson test with an option to do a randomized test
  • binom_test Vectorized one-sided binomial test with an option to do a randomized test
  • binom_test_two_sided Vectorized Two-sided binomial test with an option to do a randomized test
  • binom_test_two_sided_slow Vectorized two-sided binomial test using scipy.stats.binom_test

Example:

from twosample import bin_allocation_test, bin_variance_test
from multitest import MultiTest
import numpy as np

N = 100
n = 500
eps = 0.1
mu = 0.01

P = np.ones(N) / N
Q = P.copy()
Q[np.random.rand(N) < eps] += mu
Q = Q / Q.sum()

  
smp1 = np.random.multinomial(n, P)  # sample form P
smp2 = np.random.multinomial(n, Q)  # sample from Q

pvals_alloc = bin_allocation_test(smp1, smp2) # binomial P-values
pvals_var = bin_variance_test(smp1, smp2) # binomial P-values

mt_alloc = MultiTest(pvals_alloc)
mt_var = MultiTest(pvals_var)

print("HC(binomial_allocation) = ", mt_alloc.hc()[0])
print("HC(varaince) = ", mt_var.hc()[0])

Metadata

Release files for two-sample-binomial 0.0.4

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for two-sample-binomial 0.0.4
File Size Uploaded Provenance Actions
two-sample-binomial-0.0.4.tar.gz 5.3 kB Without provenance Details for two-sample-binomial-0.0.4.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for two-sample-binomial 0.0.4
File Interpreter ABI Platform Actions
two_sample_binomial-0.0.4-py3-none-any.whl Python 3 none any Details for two_sample_binomial-0.0.4-py3-none-any.whl

Total release size: 10.9 kB

Release files / two-sample-binomial-0.0.4.tar.gz

Download URL two-sample-binomial-0.0.4.tar.gz
Size 5.3 kB
Tags Source
SHA-256 checksum
How to use checksums
3de158e7806cf5a7cd2cbb619bcdf8ae91781c3dfeb9796fcd901e20c12210f2
BLAKE2b-256 checksum
How to use checksums
f72f97bc0c770f57710d0c969da351c37557dfad4692921abb34b0a339463d7e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.10.11

Release files / two_sample_binomial-0.0.4-py3-none-any.whl

Download URL two_sample_binomial-0.0.4-py3-none-any.whl
Size 5.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
703c023fcd78cb99753fb696a3157665de37863551e131ef6b123e2772e2f5dc
BLAKE2b-256 checksum
How to use checksums
6428f855f8d0163ad20a7b0a6cd28d2426a0aeaceeaeb41d1de28483eed9a505
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.2 CPython/3.10.11

Security for two-sample-binomial 0.0.4

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page