FREEDOM251

Freedom251 › Statistical Analysis Software

Hypothesize

by Hypothesize

Free plan LinuxMacWindows

Visit Hypothesize Alternatives

Hypothesize's own site

What Hypothesize is

Hypothesize is a free Python library for robust statistics that compares groups and measures associations. Its methods draw on Rand R. Wilcox’s WRS package and cover single-factor and multi-factor designs with independent, dependent, and mixed groups. Supported estimators can include the mean, median, trimmed mean, winsorized correlation, and percentage bend correlation. Sequentially rejective methods provide family-wise error control. Data can come from Pandas DataFrames or Series, including CSV files through Pandas. Installation uses pip install hypothesize, with Python 3.6 or newer, NumPy, Pandas, SciPy, and more-itertools listed as dependencies. Ready-to-run examples are available for top-level functions, and tests can be launched in Deepnote with sample data. The library supports scripting and statistical tests but does not list regression models. Some tests allow only trim_mean, and l2drmci cannot handle unequal sample sizes when pairwise_drop_na is false. It uses the BSD 3-Clause license.

Who it suits

It suits Python users needing robust group comparisons or association measures. Researchers can also follow the project’s requested 2020 Journal of Open Source Software citation.

What it does well

  • Free BSD 3-Clause library
  • Supports independent, dependent, and mixed designs
  • Multiple robust estimator choices
  • Pandas and CSV data input
  • Deepnote examples with sample data

What to know first

  • No regression models listed
  • Some tests only support trim_mean
  • l2drmci has an unequal-size limitation
  • Requires Python and listed dependencies

Verdict

Hypothesize offers robust statistical procedures in a Python workflow with examples and notebook access. Review the documented estimator and sample-size limits when selecting functions.

Facts from Hypothesize's own pages

Academic citation
The site requests that academic users cite Campopiano and Wilcox's 2020 Journal of Open Source Software article. · alcampopiano.github.io, 11 Oct 2026
Citation
The home page gives a 2020 Journal of Open Source Software citation with Allan Campopiano and Rand R. Wilcox as authors. · alcampopiano.github.io, 11 Oct 2026
Data import formats
Pandas DataFrames or Series; CSV via Pandas · alcampopiano.github.io, 23 Sept 2026
Dependencies
The listed dependencies are Python 3.6 or newer, NumPy, Pandas, SciPy, and more-itertools, installed automatically with the installation command. · alcampopiano.github.io, 11 Oct 2026
Deployment
desktop · alcampopiano.github.io, 23 Sept 2026
Error control
Family-wise error can be controlled with sequentially rejective methods. · alcampopiano.github.io, 11 Oct 2026
Estimator options
Where applicable, tests can use estimators such as the mean, median, trimmed mean, winsorized correlation, and percentage bend correlation. · alcampopiano.github.io, 11 Oct 2026
Estimators
Where applicable, tests let users specify estimators such as the mean, median, trimmed mean, winsorized correlation, and percentage bend correlation. · alcampopiano.github.io, 11 Oct 2026
Examples
The overview says one-click, ready-to-run examples are available for every top-level function. · alcampopiano.github.io, 11 Oct 2026
Founded
2020 · alcampopiano.github.io, 19 Oct 2026
Free plan
Yes · alcampopiano.github.io, 23 Sept 2026
Installation
The package can be installed with pip using `pip install hypothesize`. · alcampopiano.github.io, 11 Oct 2026
License
Hypothesize is licensed under the BSD 3-Clause license. · alcampopiano.github.io, 11 Oct 2026
Methods
The library brings robust statistical methods based on Rand R. Wilcox’s WRS package to Python. · alcampopiano.github.io, 11 Oct 2026
Notable function limit
The function reference says some documented tests currently support only `trim_mean` as their measure-of-location estimator. · alcampopiano.github.io, 11 Oct 2026
Notable limitation
The function reference says `l2drmci` cannot handle unequal sample sizes when `pairwise_drop_na` is false. · alcampopiano.github.io, 11 Oct 2026
Notebook integration
The GitHub README says each statistical test can be launched in Deepnote’s hosted notebook environment with sample data. · github.com, 11 Oct 2026
Purpose
Hypothesize is a Python library for robust statistics that compares groups and measures associations. · alcampopiano.github.io, 11 Oct 2026
Regression models
No · alcampopiano.github.io, 23 Sept 2026
Requirements
The listed dependencies are Python 3.6 or newer, NumPy, Pandas, SciPy, and more-itertools; the page says they install automatically with the pip command. · alcampopiano.github.io, 11 Oct 2026
Scripting support
Yes · alcampopiano.github.io, 23 Sept 2026
Statistical designs
It supports single- and multi-factor designs, including independent, dependent, and mixed groups. · alcampopiano.github.io, 11 Oct 2026
Statistical tests
Yes · alcampopiano.github.io, 23 Sept 2026
Support
The home page directs users to GitHub Issues for questions and bug reports. · alcampopiano.github.io, 11 Oct 2026

Where Hypothesize stands on Freedom251

Look at these too