search.prep {ShortForm}R Documentation

Given a fitted lavaan model (e.g., CFA), prepares a table that contains parameters that can be fixed/freed as part of a model specification search.

Description

Given a fitted lavaan model (e.g., CFA), prepares a table that contains parameters that can be fixed/freed as part of a model specification search.

Usage

search.prep(fitted.model, loadings = TRUE, fcov = TRUE, errors = FALSE)

Arguments

fitted.model

- an object of class "lavaan" that contains the initially fitted model for the search

loadings

- a logical value that indicates whether cross-loadings will be part of the search

fcov

- a logical value indicating whether factor covariances will be part of the search

errors

- a logical value indicating whether error covariances will be part of the search

Value

A data.frame with lavaan-formatted parameter values.

Author(s)

Carl F. Falk

References

doi:10.1080/10705511.2017.1409074

See Also

Other Tabu Search: add.param(), refit.model()

Examples

## Not run: 
# load simulation data and select columns used in this example
data(simulated_test_data)
tabuData <- simulated_test_data[, c(1:10)]

# specify an improper model (improper because data is unidimensional)
tabuModel <- "
Ability =~ Item1 + Item2 + Item3 + Item4
FakeAbility =~ Item5 + Item6 + Item7 + Item8
Ability ~ Outcome
FakeAbility ~ 0*Outcome"

# run the initial misspecified model for Tabu

init.model <- lavaan::lavaan(
  model = tabuModel, data = tabuData,
  auto.var = TRUE, auto.fix.first = FALSE, std.lv = TRUE, auto.cov.lv.x = TRUE
)

# Use search.prep to prepare for the Tabu search
ptab <- search.prep(fitted.model = init.model, loadings = TRUE, fcov = TRUE, errors = FALSE)

# add an additional (mispecified) parameter
additional.param <- "Item1 ~~ 0.5*Item3"
ptab <- add.param(fitted.model = init.model, ptab = ptab, syntax = additional.param)

# Perform Tabu Search
trial <- tabu.sem(init.model = init.model, ptab = ptab, obj = AIC, niter = 2, tabu.size = 5)

## End(Not run)

[Package ShortForm version 0.5.5 Index]