I'm simulating a set of data by defining a single factor model with 10 items. I want to be able to recode the scores for each item for each individual as if the responses came from a 5 point Likert scale (treated as a continuous variable). Therefore, I need to restrict the range of the simulated data to 1 and 5. Does anyone know what the best way is to do this?
Example 5.2 is a CFA with categorical factor indicators. See the input for the Monte Carlo counterpart of Example 5.2 which comes on the Mplus CD and is also available at the website. This will show how to generate categorical data. If you have 5 categories, you will need four thresholds.