piecewiseSEM (version 1.1.1)

sem.model.fits: Goodness-of-fit statistics for linear models

Description

Returns (pseudo)-R^2 and AIC values for component models in structural equation model (SEM).

Usage

sem.model.fits(modelList, aicc = FALSE)

Arguments

modelList

a list of regressions representing the structural equation model.

aicc

whether AIC corrected for small sample size (AICc) should be returned. Default is FALSE.

Value

• Returns a data.frame with the model class, the family, the link function, the marginal R^2 (based on fixed effects only) and/or conditional R^2 (based on fixed and random effects, if present), and the AIC(c) score (based on ML).

Details

Returns goodness-of-fit statistics for generalized linear (mixed) models, including (marginal and condition) R^2 and Akaike Information Criterion (AIC(c)) values.

References

Nakagawa, Shinichi, and Holger Schielzeth. "A general and simple method for obtaining R2 from generalized linear mixed-effects models." Methods in Ecology and Evolution 4.2 (2013): 133-142. Johnson, Paul C.D. "Extension of Nakagawa & Schielzeth's R2GLMM to random slopes models." Methods in Ecology and Evolution.

Examples

# Load example data
data(shipley2009)

# Load model packages
library(lme4)
library(nlme)

# Create list of models 
shipley2009.modlist = list(
  
  lme(DD ~ lat, random = ~1|site/tree, na.action = na.omit, 
      data = shipley2009),
  
  lme(Date ~ DD, random = ~1|site/tree, na.action = na.omit, 
      data = shipley2009),
  
  lme(Growth ~ Date, random = ~1|site/tree, na.action = na.omit, 
      data = shipley2009),
  
  glmer(Live ~ Growth+(1|site)+(1|tree), 
        family=binomial(link = "logit"), data = shipley2009) 
  
)

# Return model fit statistics
sem.model.fits(shipley2009.modlist)

## NOT RUN ##

# # Get R2 for linear model
# lm.mod = lm(DD ~ lat, data = shipley2009)
# sem.model.fits(lm.mod)
# 
# # Get R2 for generalized linear model
# glm.mod = glm(Live ~ Growth, family = "binomial", data = shipley2009)
# sem.model.fits(glm.mod)
# 
# # Get R2 for generalized least-squares model
# library(nlme) 
# 
# gls.mod = gls(DD ~ lat, na.action = na.omit, data = shipley2009)
# sem.model.fits(gls.mod)
# 
# # Can supply the models as a list
# # Use lm and gls -- should produce very similar R2s, will also produce delta AIC
# sem.model.fits(list(lm.mod, gls.mod))
# 
# # Get R2 for linear mixed effects model (nlme)
# lme.mod = lme(DD ~ lat, random = ~1|site/tree, na.action = na.omit, data = shipley2009)
# sem.model.fits(lme.mod)
# 
# # Get R2 for linear mixed effects model (lme4)
# library(lme4)
# 
# lmer.mod = lmer(DD ~ lat + (1|site/tree), data = shipley2009)
# sem.model.fits(lmer.mod)
# 
# # Get R2 for generalized linear mixed effects model (lme4)
# glmer.mod = glmer(Live ~ Growth + (1|site/tree), family = "binomial", data = shipley2009)
# sem.model.fits(glmer.mod)

## NOT RUN ##