|
|
CFA for longitudinal data |
|
Message/Author |
|
|
Hello, I've established measurement invariance for my variable of interest (burnout) across two time points. The CFA results in good model fit for each time point individually. However, when I attempt a latent change model, the model fit becomes terrible. Any thoughts about what the issue could be? Thank you! |
|
|
A typical source of misfit is that the residuals of the factor indicators need to be correlated across time for the same indicator. |
|
|
Thank you so much. That did help. I have a more general question about what analyses you would recommend. I am interested if the change in burnout over the course of a month (two time points) is explained by the pattern of change in energy (across 4 time points throughout the month). Do you have any recommendations for how to approach this? I am reading the Geiser MPlus book and am struggling to find an analytic approach that fits my question. |
|
|
See sequential processes in the Short Course Topic 6 video and handout slides 158-168 on our web site. |
|
|
You can also do this without mixtures and simply say s2 on s1; You would also have to think about how i2 relates to i1 and s1. See also the paper on our website: Muthén, B., Khoo, S.T., Francis, D. & Kim Boscardin, C. (2003). Analysis of reading skills development from Kindergarten through first grade: An application of growth mixture modeling to sequential processes. Multilevel Modeling: Methodological Advances, Issues, and Applications. S.R. Reise & N. Duan (Eds). Mahaw, NJ: Lawrence Erlbaum Associates, pp.71-89. download paper contact first author show abstract |
|
Back to top |
|
|