|
Message/Author |
|
|
Hello, I am interested in constructing a latent profile with 3 indicators. Could I then use class membership to predict growth trajectory in a growth mixture model? Do you know if this has been done in any published work before? Thank you for any help with this! |
|
|
Michael, This is possible to model. You can either model it by using a single categorical latent variable or by modeling two categorical latent variables and studying the transition probabilities. Song & Muthén have something similar (sequential growth model although the idea is the essentially the same for LPA+GMM) published as a working paper here: http://repositories.cdlib.org/cgi/viewcontent.cgi?article=1326&context=ccpr Sincerely, Amir |
|
|
See also: van Lier, P.A.C., Muthén, B., van der Sar, R.M. & Crijnen, A.A.M. (2004). Preventing disruptive behavior in elementary schoolchildren: Impact of a universal classroom-based intervention. In Journal of Consulting and Clinical Psychology, 72, 467-478. which is available on the website. |
|
|
Thanks for the reference, Dr. Muthén. I had missed that one. Sincerely, Amir |
|
Back to top |
|
|