Covariates PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
 Sarah Phillips posted on Friday, June 01, 2012 - 1:22 pm

I am attempting to add some observed covariates to my measurement model. I believe I am following the code correctly but when I check my Tech4 output, it appears that MPLUS is reading these covariates as latent variables instead of observed. Can you tell me what I'm doing wrong? Here's an excerpt of my code. The variables after the on are the covariates I'm trying to include. All but m_b56 are dichotomous:

BE by m_a3 m_a31 m_a28 m_b50;
BE on male onepar m_b56 grade10 grade11 grade12 schid2;

Thank you!

 Linda K. Muthen posted on Friday, June 01, 2012 - 4:48 pm
Observed variables can show up in alpha, beta, and psi. This does not mean they are latent variables. It just means this is the matrix that is being used. It makes not difference in the results.
 Sarah Phillips posted on Monday, June 04, 2012 - 8:05 am
 Vaiva Gerasimaviciute posted on Tuesday, March 29, 2016 - 6:47 am
I would like to add time-consistant and time-varying covariates to the cross-lagged model with three time points.

I2 on I1 D1;
D2 on D1 I1;
I3 on I2 I1 D2 D1;
D3 on I2 I1 D2 D1;

Question: for time-consistant variables, let's say gender, should I add it to all independent and dependent variables?:
I1 on gender;
D1 on gender;
I2 on I1 D1 gender;
D2 on D1 I1 gender;
I3 on I2 I1 D2 D1 gender;
D3 on I2 I1 D2 D1 gender;

Thank you,
 Bengt O. Muthen posted on Tuesday, March 29, 2016 - 9:35 am
You want to ask this kind of general analysis question on SEMNET.
Back to top
Add Your Message Here
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Options: Enable HTML code in message
Automatically activate URLs in message