When reporting from the Mplus output number of participants assigned to classes are we referring to?
1. FINAL CLASS COUNTS AND PROPORTIONS FOR THE LATENT CLASSES
BASED ON THE ESTIMATED MODEL
2. FINAL CLASS COUNTS AND PROPORTIONS FOR THE LATENT CLASSES
BASED ON ESTIMATED POSTERIOR PROBABILITIES
3. FINAL CLASS COUNTS AND PROPORTIONS FOR THE LATENT CLASSES
BASED ON THEIR MOST LIKELY LATENT CLASS MEMBERSHIP
Thank you for clarifying
Witold
Pl read the topics with multiple answers,
http://www.statmodel.com/discussion/messages/13/115.html
Hi Witold,
1. und 2. should be identical for a good fitting model, the second is based on an Bayesian approach (as far a I can see). 3. is an alternative method of assigning individuals to classes.
Here is some explanation that may be helpful for you:
https://stats.idre.ucla.edu/mplus/seminars/intromplus-part2/mplus-class-notesanalyzing-data-latent-class-and-other-mixture-models/
Kind regards,
Karin
Depending on the software being used, these are values you can get from model output. What software is being used for this latent class analysis?
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics