semEff provides functionality to automatically calculate
direct, indirect, and total effects for ‘piecewise’ structural equation
models, comprising lists of fitted models representing structured
equations (Lefcheck, 2016; Shipley, 2000, 2009). Confidence intervals
are provided via bootstrapping.
Currently supported model classes are "lm",
"glm", "lmerMod", "glmerMod",
"lmerModLmerTest", "gls", and
"betareg".
You can install the released version of semEff from CRAN with:
install.packages("semEff")And the development version from GitHub with:
devtools::install_github("murphymv/semEff@dev")The primary function is semEff(),
which returns an object of class "semEff" with associated
print() and summary() methods. Everything can
technically be accomplished in a single call to semEff();
however, since bootstrapping is employed to generate resamples for
confidence intervals (via bootEff()),
it is usually preferable to save these estimates separately prior to
calling semEff() – allowing more flexibility and saving
time if/when recalling the function.
Package functions are well-documented and most include some short examples. In addition, see the following vignettes for some longer demonstrations:
Analysing direct vs. indirect effects of landscape location on plant species richness
Predicting and plotting indirect effects of degree days to bud burst on tree growth
Lefcheck, J. S. (2016). piecewiseSEM: Piecewise structural equation modelling in R for ecology, evolution, and systematics. Methods in Ecology and Evolution, 7(5), 573–579. https://doi.org/10/f8s8rb
Shipley, B. (2000). A New Inferential Test for Path Models Based on Directed Acyclic Graphs. Structural Equation Modeling: A Multidisciplinary Journal, 7(2), 206–218. https://doi.org/10/cqm32d
Shipley, B. (2009). Confirmatory path analysis in a generalized multilevel context. Ecology, 90(2), 363–368. https://doi.org/10/bqd43d