piecewiseSEM (version 1.2.1)

piecewiseSEM-package: Piecewise Structural Equation Modeling

Description

Implements piecewise structural equation modeling in R, complete with goodness-of-fit tests and retrieval of model coefficients. Compared with traditional variance-covariance based SEM, piecewise SEM allows for fitting of models to different distributions and/or incorporates hierarchical/nested random structures.

Supported model classes include: `lm`, `rq`, `glm`, `glm.nb`, `gls`, `pgls`, `merMod`, `merModLmerTest`, `lme`, `glmmPQL`, `glmmadmb`, and `glmmTMB`.

Details

Package:	piecewiseSEM
Type:	Package
Version:	1.2.1
Date:	2016-12-06
Depends:	R (3.3), ggm, lavaan, nlme, pbkrtest
Suggests:	MASS, lme4
License:	MIT

The primary functions in the package are sem.fit which performs goodness-of-fit tests, and sem.coefs which returns path coefficients (standardized, if specified) and standard errors.

References

Shipley, Bill. "A new inferential test for path models based on directed acyclic graphs." Structural Equation Modeling 7.2 (2000): 206-218.

Shipley, Bill. Cause and correlation in biology: a user's guide to path analysis, structural equations and causal inference. Cambridge University Press, 2002.

Shipley, Bill. "Confirmatory path analysis in a generalized multilevel context." Ecology 90.2 (2009): 363-368.

Shipley, Bill. "The AIC model selection method applied to path analytic models compared using a d-separation test." Ecology 94.3 (2013): 560-564.

Examples

# NOT RUN {
# Load example data
data(shipley2009)

# Reduce dataset for example
shipley2009.reduced = shipley2009[1:200, ]

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

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

# Extract path coefficients
sem.coefs(shipley2009.reduced.modlist, shipley2009.reduced)

# }
# NOT RUN {
  # Repeat with full dataset as in Shipley (2009)

  # 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) 
    
  )
  
  # Get goodness-of-fit and AIC
  sem.fit(shipley2009.modlist, shipley2009)
  
  # Extract path coefficients
  sem.coefs(shipley2009.modlist, shipley2009)
  
# }