Mon - Fri : 08:00 AM - 5:00 PM

Structural Equation Modeling Using Mplus

Structural Equation Modeling Using Mplus


This page presents Mplus syntax to estimate the full SEM described in the running example. The data can be downloaded from here, and a tutorial on preparing data for Mplus using SPSS can be found here. Estimating the model requires a full Mplus license; the number of dependent variables exceeds the limit imposed by the demo version. Thus, only the syntax is presented here. The output, however, will be similar to what is obtained by other programs.

The Mplus syntax to estimate the full SEM is the following:

DATA:       FILE IS sem_data.dat;
VARIABLE:   NAMES ARE reading writing math analytic
                simpsons famguy amerdad;
MODEL:       intell BY reading* writing math analytic;
             [email protected];
             humor BY simpsons famguy amerdad;
             humor ON intell;
OUTPUT:      standardized;

The first statement gives the model a title, and the DATA statement points to the location of the data file. If the input file is saved to the same directory as the data file, then it is only necessary to enter the data file name. The next line, VARIABLE, defines the names of the variables in the data. There is an additional USEVARIABLES option that can be used to specify which variables in the file will be used in the model. In this case, the option is not necessary because all variables will be used.

The MODEL statement then defines the model. In this case, there will be a latent variable named intell which is measured BY the four observed test score variables, and another latent variable names humor which measured BY reviews of the three television shows. In addition, the humor variable will be regressed ON intelligence. Notice the change in preposition to indicate the difference between the measurement and structural components of the model.

The model is identified by setting the scales of the latent variables. The default in Mplus is for the scale to be set by constraining the factor loading of the first variable to equal one. The default is used in this example for the humor variable, but the scale for intell is set by constraining its variance to equal one. This is done by adding an asterisk after reading (to free its loading) and adding a line with [email protected]. The final OUTPUT statement is optional and used to request additional information in the output file. In this case, standardized estimates are requested.

After specifying the syntax, save the input file in the same directory as the data and click RUN. This writes an output file (.out extension) to the same directory as the input file.

Still have questions? Contact us!