Structural Equation Model (SEM) Example

Table of Contents

1 Title Command

This is an example of a structural equation model with latent variables being evaluated an dependent variables in regression.

TITLE:
Example 5 - Structural Equation Model

2 Data Command

DATA:
FILE IS "../../data/job_placement.csv";

3 Variable Command

The data are imported the same way as before, but notice the change under the "USEVARIABLES ARE" statement.

VARIABLE:
NAMES ARE
id wjcalc wjspl wratspl wratcalc waiscalc waisspl
edlevel newschl suspend expelled haveld female age;

USEVARIABLES ARE
wratspl wjspl waisspl wratcalc wjcalc waiscalc
edlevel newschl suspend expelled haveld female age;

MISSING ARE all(99999);

4 Model Command

Here is an example of a SEM with measurement (CFA) and prediction (MLR) components combined. The first three lines set up the measurement of the MATH and SPELL latent variables. The remaining lines build the structural portion of the model in which each latent variable is predicted by seven observed variables and the latent variables are allowed to correlate (this is done by the WITH statement).

MODEL:
MATH BY wratcalc wjcalc waiscalc;
SPELL BY wratspl wjspl waisspl;
MATH ON edlevel newschl suspend expelled haveld female age;
SPELL ON edlevel newschl suspend expelled haveld female age;
MATH WITH SPELL;

5 Analysis Command

As always, additional output can be requested.

OUTPUT:
SAMPSTAT; 
TECH1;
STDYX;

Date: 2016-09-12T14:52-0500

Author: Benjamin Arthur Kite

Org version 7.9.3f with Emacs version 24

Validate XHTML 1.0