I am new to latent growth curve models, and for examples I read from Mplus users guide, it seems time invariant variables are often used to explain the Intercept and Slope of the overall trajectory.
I am not sure what part of trajectory time-varying variables explain?
Do time-varying variables affect the Intercept and the Slope?
Jon Heron posted on Monday, July 25, 2016 - 1:36 am
time-varying variables predict the actual repeated measures. As such they enable you to tease apart within- and between- person effects.
Patrick Curran and colleagues have a number of papers and a book chapter on these models.
e.g. Hussong, A.M., Curran, P.J., Moffitt, T.E., Caspi, A., & Carrig, M.M. (2004). Substance abuse hinders desistance in young adults' antisocial behavior. Development and Psychopathology, 16, 1029-1046.