███╗   ███╗  ██████╗ ██████╗ 
████╗ ████║ ██╔════╝ ██╔══██╗ ██████╗ ██╗    ██╗███████╗██████╗ 
██╔████╔██║ ██║      ██║  ██║██╔═══██╗██║    ██║██╔════╝██╔══██╗
██║╚██╔╝██║ ██║      ██████╔╝██║   ██║██║ █╗ ██║█████╗  ██████╔╝
██║ ╚═╝ ██║ ██║      ██╔═══╝ ██║   ██║██║███╗██║██╔══╝  ██╔══██╗
██║     ██║ ╚██████╗ ██║     ╚██████╔╝╚███╔███╔╝███████╗██║  ██║
╚═╝     ╚═╝  ╚═════╝ ╚═╝      ╚═════╝  ╚══╝╚══╝ ╚══════╝╚═╝  ╚═╝

MCPower GUI

MCPower GUI is a desktop application for Monte Carlo power analysis. It provides a graphical interface to the MCPower library, letting you plan sample sizes and estimate statistical power for complex study designs — without writing any code.

Download

| Platform | Link | |---|---| | Windows | MCPower.exe | | Linux | MCPower-linux | | macOS | MCPower-macos |

No Python installation required — these are standalone executables.

Windows

Download MCPower.exe.
Double-click to run.

Note: Windows SmartScreen may show a warning ("Windows protected your PC") because the application is not code-signed. Code signing certificates cost ~$100/year, which is not feasible for a free open-source project. The app is safe — you can verify the source code in this repository. To proceed: click More info → Run anyway.

Your antivirus software may also flag the file. This is a known false positive caused by the packaging tool (PyInstaller) used to create standalone Python executables. Many legitimate open-source applications trigger the same warning.

Linux

Download MCPower-linux.
Open a terminal in the download folder:
- File manager: Right-click in the folder → Open Terminal Here
- Or manually: open a terminal and run cd ~/Downloads
Make the file executable and run it:
```
chmod +x MCPower-linux
./MCPower-linux
```

macOS

Download MCPower-macos.
Open Terminal in the download folder:
- Open Finder → navigate to the Downloads folder → right-click the folder in the sidebar → Services → New Terminal at Folder
- Or manually: open Terminal and run cd ~/Downloads
Make the file executable:
```
chmod +x MCPower-macos
```
Run the app: right-click MCPower-macos in Finder → Open (required on first launch to bypass Gatekeeper, since the app is not signed with an Apple Developer certificate).

Full documentation is available in-app via the Documentation menu item.

What is power analysis?

Statistical power is the probability that a study will detect a real effect when one exists. A power analysis helps you determine:

Find Power: Given a sample size, what is the probability of detecting your expected effects?
Find Sample Size: What sample size do you need to achieve a target power level (e.g., 80%)?

Why Monte Carlo simulation?

Traditional power formulas work for simple designs but break down with interactions, correlated predictors, categorical variables, or non-normal data. MCPower uses Monte Carlo simulation — it generates thousands of synthetic datasets under your assumptions, fits the statistical model to each, and counts how often the effects are detected. This approach handles arbitrary complexity.

App workflow

Model tab — Define your study design: enter a formula, set variable types, specify effect sizes, and optionally upload empirical data with correlations.
Analysis tab — Choose analysis mode (Find Power or Find Sample Size), set target power, enable scenarios, and select multiple testing corrections.
Results tab — View power tables, bar charts, power curves, scenario comparisons, and a replication script you can run independently.

Formula syntax

MCPower uses R-style formula notation:

| Formula | Meaning | |---|---| | y = x1 + x2 | Two main effects | | y = x1 + x2 + x1:x2 | Two main effects + interaction | | y = x1 * x2 | Shorthand for x1 + x2 + x1:x2 | Both = and ~ are accepted as separators between the dependent variable and predictors.

Note: Mixed-effects models (e.g., y ~ x + (1|school)) are supported by the MCPower library but are not yet available in the GUI. Mixed model support in the app is planned for a future release.

Built on

MCPower GUI is built on MCPower.

License & Citation

GPL v3. If you use MCPower in research, please cite:

Lenartowicz, P. (2025). MCPower: Monte Carlo Power Analysis for Statistical Models. Zenodo. DOI: 10.5281/zenodo.16502734

@software{mcpower2025,
  author = {Pawel Lenartowicz},
  title = {MCPower: Monte Carlo Power Analysis for Statistical Models},
  year = {2025},
  publisher = {Zenodo},
  doi = {10.5281/zenodo.16502734},
  url = {https://doi.org/10.5281/zenodo.16502734}
}

Support

This project is free and open-source. If you'd like to support its development, donations are appreciated!

Support this project

MCP Servers