partR2-package: partR2: Partitioning R2 in generalized linear mixed models

Description Details References


The partR2 package provides a simple way to estimate R2 in mixed models fitted with lme4 as well as part (semi-partial) R2 for specific predictors and combinations of predictors, among other several other statistics. Here is an overview:


The package has one main function partR2 which takes a fitted model from lme4. At the moment, Gaussian, Poisson and binomial models are supported. For Poisson and non-binary binomial models, partR2 adds an observational level random effect to model additive overdispersion (if an olre is not fitted already).

The summary.partR2 function provides an extended summary with R2s, semi-partial R2s, model estimates and structure coefficients. The forestplot function provides a means of plotting the results.


Nakagawa, S., & Schielzeth, H. (2013). A general and simple method for obtaining R2 from generalized linear mixed-effects models. Methods in Ecology and Evolution, 4(2), 133-142.

Nakagawa, S., Johnson, P. C., & Schielzeth, H. (2017). The coefficient of determination R2 and intra-class correlation coefficient from generalized linear mixed-effects models revisited and expanded. Journal of the Royal Society Interface, 14(134), 20170213.

partR2 documentation built on Jan. 18, 2021, 5:06 p.m.