17 Help

17.1 Giving help

The marginaleffects package and the Marginal Effects Zoo online book will always be free. If you like this project, you can contribute in four ways:

Make a donation to the Native Women’s Shelter of Montreal or to Give Directly, and send me (Vincent) a quick note. You’ll make my day.
Submit bug reports, documentation improvements, or code contributions to the Github repositories of the R version or the Python version of the package.
Create a new entry for the Meme Gallery!
Cite the marginaleffects package in your work and tell your friends about it.

To cite marginaleffects in publications use:

Arel-Bundock V, Greifer N, Heiss A (2024). “How to Interpret Statistical Models Using marginaleffects for R and Python.” Journal of Statistical Software, 111(9), 1-32. doi:10.18637/jss.v111.i09 https://doi.org/10.18637/jss.v111.i09.

A BibTeX entry for LaTeX users is

@Article{,
  title = {How to Interpret Statistical Models Using {marginaleffects} for {R} and {Python}},
  author = {Vincent Arel-Bundock and Noah Greifer and Andrew Heiss},
  journal = {Journal of Statistical Software},
  year = {2024},
  volume = {111},
  number = {9},
  pages = {1--32},
  doi = {10.18637/jss.v111.i09},
}

17.2 Getting help

If you need help with marginaleffects, there are several possible venues:

Statistical question: Ask on Cross Validated, using the marginal-effect tag.
Programming question: Ask on Stack Overflow, using the r-marginaleffects tag.
Post on the marginaleffects discussions forum on Github. Warning: Stack Overflow and Cross Validate have much more traffic than the forum. So you have a greater chance of getting an answer there.

It is considered polite to avoid posting on multiple sites at once.

When you ask for help, you will have a much better chance of obtaining useful answers if you provide an example with these characteristics:

Public data:
- Use a publicly available dataset like mtcars or a CSV from the Rdatasets archive.
Minimal:
- Avoid loading irrelevant libraries and extra code. Only show the relevant bits.
Errors & warnings:
- Show the complete errors and warnings. They are usually informative.
Cut & paste:
- Make sure we can just copy your entire code and paste it directly into an R console to reproduce your problem. People are much less likely to take the time to investigate if they have to clean up your code before they can use it. For example, do not supply the console output with + at the start of each line. This output is not executable.
sessionInfo()
- Paste the output of this command at the bottom of your question so we know in what environment the code is run and what package versions are used.

For more information about asking good questions about software, see this classic post on Stack Overflow: https://stackoverflow.com/a/5963610/342331

Finally, remember that the people who maintain, contribute, and answer questions about marginaleffects do it for free, on nights and weekends. Please be patient. And please be forgiving if we do not find the time to answer your question at all.

17.3 Bugs and feature requests

To report bugs or feature requests, please visit the Github issue tracker here: