Log Transformed Values in Parallel Pr... PreviousNext
Mplus Discussion > Latent Variable Mixture Modeling >
Message/Author
 Oleg Zaslavsky posted on Friday, December 27, 2013 - 1:23 am
Dear Mplus support group,
I am using parallel process growth mixture modeling to estimate longitudinal dynamics between pain and sleep measures.
Conceptually speaking if I log transform both of these raw measures and then regress their latent variables (intercept and slope) on each other, should I interpret that model estimates as percentage change in x that is linked to percentage change in y.
Thanks in advance for your prompt reply
Oleg Zaslavsky
 Bengt O. Muthen posted on Friday, December 27, 2013 - 11:50 am
I don't see that. You may want to ask this general question on Multilevelnet.
 Oleg Zaslavsky posted on Thursday, January 02, 2014 - 3:46 am
Dr. Muthen,
Thanks a lot for your prompt reply.
As you suggested I posted the question on Multilevelnet and received conflicting messages. Some suggested that I can refer to that relationship as to elastic and some disagreed. Will really appreciate your take on the dilemma: If I regress the estimates (intercepts and slopes) from the LCGM which were calculated using log transform raw values in both measures on each other, will elasticity come into effect in linear regression model?
 Bengt O. Muthen posted on Thursday, January 02, 2014 - 10:31 am
I don't see how that would come about.
 Bengt O. Muthen posted on Thursday, January 02, 2014 - 11:09 am
Perhaps the econometrics literature would help you.
 Oleg Zaslavsky posted on Friday, January 03, 2014 - 4:31 am
Thanks a lot for the response
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Password:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: