Skip to main content

Bayesian estimation supersedes the t-test

Project description

BEST: Bayesian Estimation Supersedes the t-Test

Python implementation of a Bayesian model to replace t-tests with Bayesian estimation, following the idea described in the following publication:

John K. Kruschke. Bayesian estimation supersedes the t test. Journal of Experimental Psychology: General, 2013, v.142 (2), pp. 573-603. (doi: 10.1037/a0029146)

The package implements Bayesian estimation of the mean of one or two groups, and plotting functions for the posterior distributions of variables such as the effect size, group means and their difference.

Documentation

See the documentation for more information, at best.readthedocs.io.

Requirements

Examples

A complete analysis and plotting is done in just a few lines:

>>> best_out = best.analyze_two(group1_data, group2_data)
>>> fig = best.plot_all(best_out)
>>> fig.savefig('best_plots.pdf')

For example, the two-group analysis in examples/smart_drug.py produces the following output:

smart_drug.png

More detailed analysis of the same data can be found in the Jupyter notebook examples/Smart drug (comparison of two groups).ipynb.

An example single-group analysis can be found in examples/paired_samples.py.

The documentation describes the API in detail.

Installation

Ensure your Python version is sufficiently up-to-date (at least 3.7):

$ python --version
Python 3.7.12

Then install this package and its dependencies with PIP:

$ pip install best

Developer notes

Tests

Running the tests requires pytest (pip install pytest), and then can be run with:

$ python -m pytest tests

The plotting tests only ensure that the plot_all function does not throw errors, and the plots need manual verification at tests/data/plot_all_*.pdf.

Documentation

The documentation can be built with Sphinx:

$ cd docs
$ make html

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

best-2.0.5.tar.gz (13.4 kB view details)

Uploaded Source

Built Distribution

best-2.0.5-py3-none-any.whl (13.4 kB view details)

Uploaded Python 3

File details

Details for the file best-2.0.5.tar.gz.

File metadata

  • Download URL: best-2.0.5.tar.gz
  • Upload date:
  • Size: 13.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.7.1 importlib_metadata/4.5.0 pkginfo/1.8.2 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.61.1 CPython/3.8.10

File hashes

Hashes for best-2.0.5.tar.gz
Algorithm Hash digest
SHA256 3077b43667a24ac1048de526a3a1f6cc640146cf9477dbbc56aeec2d8d32700b
MD5 f9d172e5defa756db62fecf951f86399
BLAKE2b-256 dd4714e19527f2b592be3483a918c663a4d1219f13172c456de2cf3879a9f2a6

See more details on using hashes here.

File details

Details for the file best-2.0.5-py3-none-any.whl.

File metadata

  • Download URL: best-2.0.5-py3-none-any.whl
  • Upload date:
  • Size: 13.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.7.1 importlib_metadata/4.5.0 pkginfo/1.8.2 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.61.1 CPython/3.8.10

File hashes

Hashes for best-2.0.5-py3-none-any.whl
Algorithm Hash digest
SHA256 d5fff155b2b68dd62c253795dd7f633046e2529a52b2052babed6941e1d5a48d
MD5 7c165e4e13540f95ad88fd766e6bcf6b
BLAKE2b-256 3020c146c408c2fb81d81f2c2f926672acf1490f847def800c2eebc39f5d3168

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page