lessSEM2Lavaan: lessSEM2Lavaan

In lessSEM: Non-Smooth Regularization for Structural Equation Models

lessSEM2Lavaan

Description

Creates a lavaan model object from lessSEM (only if possible). Pass either a criterion or a combination of lambda, alpha, and theta.

Usage

lessSEM2Lavaan(
  regularizedSEM,
  criterion = NULL,
  lambda = NULL,
  alpha = NULL,
  theta = NULL
)

Arguments

regularizedSEM	object created with lessSEM
criterion	criterion used for model selection. Currently supported are "AIC" or "BIC"
lambda	value for tuning parameter lambda
alpha	value for tuning parameter alpha
theta	value for tuning parameter theta

Value

lavaan model

Examples

library(lessSEM)

# Identical to regsem, lessSEM builds on the lavaan
# package for model specification. The first step
# therefore is to implement the model in lavaan.

dataset <- simulateExampleData()

lavaanSyntax <- "
f =~ l1*y1 + l2*y2 + l3*y3 + l4*y4 + l5*y5 + 
     l6*y6 + l7*y7 + l8*y8 + l9*y9 + l10*y10 + 
     l11*y11 + l12*y12 + l13*y13 + l14*y14 + l15*y15
f ~~ 1*f
"

lavaanModel <- lavaan::sem(lavaanSyntax,
                           data = dataset,
                           meanstructure = TRUE,
                           std.lv = TRUE)

# Regularization:
regularized <- lasso(lavaanModel,
                     regularized = paste0("l", 11:15), 
                     lambdas = seq(0,1,.1))

# using criterion
lessSEM2Lavaan(regularizedSEM = regularized, 
               criterion = "AIC")
               
# using tuning parameters (note: we only have to specify the tuning
# parameters that are actually used by the penalty function. In case
# of lasso, this is lambda):
lessSEM2Lavaan(regularizedSEM = regularized, 
               lambda = 1)

lessSEM documentation built on May 29, 2024, 7:10 a.m.