The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.

partR2

The goal of partR2 is to estimate R² in GLMMs (sensu Nakagawa & Schielzeth 2013) and to partition the R² into the variance explained by the predictors.

The package takes a fitted lme4 model as input and gives you:

• R² (marginal or conditional)
• Part (semi-partial) R², the variance explained uniquely by each predictor and combinations of predictors
• Inclusive R², the variance explained by a predictor independent of all other predictors
• Structure coefficients, the correlation between a predictor and the fitted response
• Beta weights, standardised model estimates

All estimates can be combined with parametric bootstrapping to get confidence intervals.

Installation

You can install the stable version of partR2 from CRAN with:

install.packages("partR2")

Or the development version from GitHub with:

# install.packages("remotes")
remotes::install_github("mastoffel/partR2", build_vignettes = TRUE, dependencies = TRUE) 

Access the vignette with:

# check vignette
browseVignettes("partR2")

partR2 is still in an early phase of development and might contain bugs. If you find one, please report a minimal reproducible example in the issues.

Citation

When using partR2, please cite our paper:

Stoffel MA, Nakagawa S, Schielzeth H. 2021. partR2: partitioning R2 in generalized linear mixed models. PeerJ 9:e11414 https://doi.org/10.7717/peerj.11414

Example

library(partR2)
library(lme4)

?`partR2-package`

# load data
data(biomass)
# fit lme4 model
mod <- lmer(Biomass ~  Year + Temperature + SpeciesDiversity + (1|Population),
            data = biomass)
# R2s and partial R2s
(R2 <- partR2(mod,  partvars = c("SpeciesDiversity", "Temperature", "Year"),
              R2_type = "marginal", nboot = 100, CI = 0.95))
#> 
#> 
#> R2 (marginal) and 95% CI for the full model: 
#>  R2     CI_lower CI_upper nboot ndf
#>  0.5133 0.4439   0.5908   100   4  
#> 
#> ----------
#> 
#> Part (semi-partial) R2:
#>  Predictor(s)                      R2     CI_lower CI_upper nboot ndf
#>  Model                             0.5133 0.4439   0.5908   100   4  
#>  SpeciesDiversity                  0.1729 0.0736   0.2913   100   3  
#>  Temperature                       0.3058 0.2193   0.4106   100   3  
#>  Year                              0.0140 0.0000   0.1537   100   3  
#>  SpeciesDiversity+Temperature      0.4916 0.4205   0.5714   100   2  
#>  SpeciesDiversity+Year             0.1862 0.0883   0.3029   100   2  
#>  Temperature+Year                  0.3276 0.2430   0.4293   100   2  
#>  SpeciesDiversity+Temperature+Year 0.5133 0.4439   0.5908   100   1

And to plot the results:

forestplot(R2, type = "R2", line_size = 0.7, text_size = 14, point_size = 3)

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.