The other day, Kevin Darras contacted me about my R package influence.ME. The package didn’t work with the kind of models he wanted to estimate, and Kevin was looking for a solution. He had been able to go ‘under the hood’ of the program code in influence.ME and to program a solution, which he kindly shared with me. After some testing, and some adjustments, the influence.ME package is now updated and uploaded to CRAN, available for anyone to use. That’s well within a week after his first e-mail.

This is why I love the open source community so much. Not only can users extend the use of influence.ME, and all other R packages, to do things that the package authors/maintainers did not implement. Or to check procedures. Or fix mistakes. Moreover, in line with the positive attitude towards sharing in the open access community, the improved code was shared back so that other users can benefit.

So, thanks to the help of the community, I am happy to announce an update to influence.ME, with two improvements:

• influence.ME now better handles binomial models
• influence.ME now supports functions inside the model call;for instance:
  model.a <- lmer(math ~ structure + scale(SES) + (1 | school.ID), data=school23)

influence.ME is an extension package for the R statistical software. It provides tools for detecting influential data in multilevel regression models (also known as mixed effects models). It was introduced in the R Journal (Nieuwenhuis, Te Grotenhuis & Pelzer, 2012). influence.ME can be downloaded from with the R software.

Nieuwenhuis, R., Grotenhuis, te, H. F., & Pelzer, B. J. (2012). Influence. ME: tools for detecting influential data in mixed effects models. R Journal, 4(2), 38–47.