Message/Author 

Anonymous posted on Sunday, March 06, 2005  8:43 am



Hello, I'm new to growth modeling. I have poisson data that I would like to examine for subgroups. The analysis that I want to perform is one that is presented by Nagin (1999). As I have read through the Mplus User's guide 3.11, which is awesome by the way, I am confused as to which GMM model I should use, and which plots command (1,2,or 3) will give a line graph with the subgroups? The key for me is to determine the subgroups. I think I understand how to put the covariates in to explain the subgroups at a conceptual level, but I need some guidance as to which model in the User's guide I should follow for the initial grouping? Thank you. 


It would be Example 8.11 with the addition of covariates. The Nagin model is a LCGA not a GMM. Example 6.10 illustrates the addition of timeinvariant and timevarying covariates. Ask for PLOT3. Then you will get as much as is available. 

Anonymous posted on Sunday, March 06, 2005  9:09 am



Thank you so much for the help and the quick response! The Mplus product is awesome. 


Hi, I'm doing a basic Latent Growth Model and I want to know if there any rule about how many covariates that we can put in the conditional model? Thank You 


There is no rule that I know of regarding the number of covariates. The group of covariates should be thoughtfully selected. 

Carolin posted on Monday, July 25, 2011  2:16 am



Hello, is there any critical value concerning the smallest class size in growth mixture modeling? If so, do you know any references? Thank you! 


Not that I know of. 


Dear Linda and Bengt, Is it valid to estimate a growth mixture model for two separate DVs, such as two slopes and two intercepts? For example: ix sx  x1@0 x2@1 x3@2; iy sy  y1@0 y2@1 y3@2; If it is valid, have you seen it in the literature? Thanks! 


One can estimate a growth mixture model for more than one process. I don't know of any reference. You could search under parallel or sequential processes. 


Thanks! 

Back to top 