In the model that is showed in the following picture the latent variables FE, FR and CC are known (they have been simulated from previous studies). I wonder if is is possible to generate Likert scales from Q2.1 to Q2.6 (7 point Likert scales) that average the known values of FE. The same for FR and Q3.1 to Q3.6 (7 point Likert scales); and finally CC and Q6.1 to Q6.12 (binary scales).

# Simulate likert scale from a model with known latent variables

I think you are asking how to create a set of variables that average to a specific value?

Simulate Q1-5 as normal, then solve

```
FE = 1/6*Q2.1 + 1/6*Q2.2 +1/6*Q2.3 +1/6*Q2.4 +1/6*Q2.5 + 1/6*Q2.6
```

for

```
Q2.6 = 6*FE - Q2.1 - Q2.2 - Q2.3 - Q2.4 - Q2.5
```

and use that to make the final item.

Thank you, Neal. It works perfectly.

MRM