fit.simulation {MonteCarloSEM}

This function runs a model for simulated data by using the lavaan package.

Description

Generated data sets (Generated by sim.skewed() or sim.normal() functions) will be fitted to pre-specified model. The lavaan package is used to fit the model. After running the model, fit indices and parameters estimated with their standard errors will be printed to a Comma Separated Values (CSV) file. The name of the output file is "All_Results.csv". Each line in the file represents the results of a simulation. The columns are self-explanatory but the second column (named Notes) needs a more detailed explanation. This column shows if the model convergency. If the model is converged without any problem the value will be "CONVERGE" If it is not converged the value will be "NONCONVERGE" and all the values in the line will be "NA" If there are some kind of warnings (such as negative variance) during the model run the value will be "WARNING" and based on the warning type some of the values might be "NA". To run the simulation, previously generated (either with the package functions or any other software) data sets and the list of the data sets (i.e., "Data_List.dat") should be located in the same folder in the working directory.

Usage

fit.simulation(
  model,
  PEmethod = "ML",
  Ordered = FALSE,
  dataList = "Data_List.dat",
  f.loc,
  missing = NULL
)

Arguments

model

Lavaan model

PEmethod

Parameter estimation method. The default is ML.

Ordered

Logical, TRUE means that the data will be defined as ordered.

dataList

List of the names of data sets generated earlier either with the package functions or any other software.

f.loc

File location. It indicates where the simulated data sets and "dataList" are located.

missing

as in the lavaan package (See lavOptions)

Author(s)

Fatih Orcan

Examples

#   Data needed to be generated at the first step.
fc<-fcors.value(nf=3, cors=c(1,.5,.6,.5,1,.4,.6,.4,1))
fl<-loading.value(nf=3, fl.loads=c(.5,.5,.5,0,0,0,0,0,0,0,0,.6,.6,.6,0,0,0,0,0,0,0,0,.4,.4))
sim.normal(nd=10, ss=100, fcors=fc, loading<-fl,  f.loc=tempdir())

#  Then simulation should be run at the second step.
lavaanM<-'
#CFA Model
f1	=~ NA*x1 + x2 + x3
f2	=~ NA*x4 + x5 + x6
f3 =~ NA*x7 + x8
#Factor Correlations
f1	~~ f2
f1	~~ f3
f2	~~ f3
#Factor variance
f1	~~ 1*f1
f2	~~ 1*f2
f3	~~ 1*f3
'
dl<-"Data_List.dat"  # should be located in the working directory.

# Note that this function uses data sets and the list files which were generated previously.
# If there are no such a data sets and the list file, it will print an error message
#  saying "cannot open the connection"

fit.simulation(model=lavaanM, PEmethod="MLR", Ordered=FALSE, dataList=dl, f.loc=tempdir())