Hi, I am fitting a LCA model to a set of longitudinal repeated binary items. A growth model is not used as the interest is in the various patterns of response over time, which may not fit a specific linear form. To account for missing data due to dropout, I wish to fit a NMAR model using a joint continuous time survival model. Is it possible to do this in MPLUS? And if so is there an example? So far I can only find examples using growth models relating survival the continuous latent intercept and slope variables, rather than a categorical latent variable. Thanks
The first issue you mention is handled simply by doing LCA with the binary items at all timepoints as latent class indicators; this doesn't require specifying a growth curve shape.
The second issue is illustrated by our new paper:
Muthén, B. & Asparouhov T. (2014). Growth mixture modeling with non-normal distributions.
- see Section 4.1.
For Mplus input, see also ex 8.17 (very similar to your situation) on page 14 of
Version 7.2 Mplus Language Addendum
See also Papers under Survival Analysis on our website, such as
Muthén, B., Asparouhov, T., Boye, M., Hackshaw, M. & Naegeli, A. (2009). Applications of continuous-time survival in latent variable models for the analysis of oncology randomized clinical trial data using Mplus. Technical Report. Click here to view Mplus outputs used in this paper.