Message/Author |
|
|
Is there a way to obtain residual from the multiple cause equation (latent variable regressed on covariates) in a MIMIC model? Any references which discuss residual estimation for MIMIC models would be very helpful. |
|
|
The RESIDUAL option gives residuals for the observed variables in the model. |
|
|
Thanks for the response. I was looking for the residual for the latent endogenous variable in the multiple cause equation in the MIMIC model. Is it possible to obtain that? Or are there any papers which talk about how to obtain it? Thanks. |
|
|
To get a residual, you need an observed value to compare the model estimated value to. I'm not sure what that would be for a latent variable. Perhaps, it could be a factor score but I don't think that would be a good choice. You might want to pose this question on a general discussion forum like SEMNET. |
|
Back to top |