Latent Classes with different durations? PreviousNext
Mplus Discussion > Latent Variable Mixture Modeling >
 Simon Racicot posted on Monday, April 18, 2011 - 12:52 pm

I'm a new Mplus user and I would like to ask a question re Growth Mixture Modeling.

I'm measuring an outcome (nicotine dependence) over 20 survey cycles. I want to create latent classes based on the development and change of nicotine dependence over 20 cycles. However, when people stop smoking, they are excluded from the survey cycle they report smoking cessation until the end of the study (cycle 20). Other participants, however, remain smokers and have data for 20 cycles.

Here's my question. Given that some participants are censored while others are not, can I have latent classes that are of shorter durations than others? Is it possible to model this reality with Mplus and GMM?
 Bengt O. Muthen posted on Tuesday, April 19, 2011 - 10:40 am
This situation sounds somewhat similar to the one in

Muthén, B., Asparouhov, T., Hunter, A. & Leuchter, A. (2011). Growth modeling with non-ignorable dropout: Alternative analyses of the STAR*D antidepressant trial. Psychological Methods, 16, 17-33.

which is on our web site under Papers, Missing Data. Some growth mixture classes are more likely to "drop out" - or be moved out of the study, which corresponds to your smoking cessation.
Back to top
Add Your Message Here
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Options: Enable HTML code in message
Automatically activate URLs in message