|
Message/Author |
|
|
I am running a growth mixture model and do not know how I should treat the residuals. It seems to me the residuals should be allowed to vary across latent class. Is this correct? Within class, should I constrain them to be equal across time or allow them to be freely estimated across time? Thank you! |
|
|
The Mplus defaults are that the residual variances are free across time and equal across classes. I would start with the defaults and look at plots to see if the equality across classes needs to relaxed for one or more classes. |
|
Back to top |
|
|