Standardized solutions in two level m... PreviousNext
Mplus Discussion > Multilevel Data/Complex Sample >
Message/Author
 Luo Wenshu posted on Tuesday, April 10, 2012 - 7:08 pm
Dear Prof. Muthen,

I are running two level path analysis. The model has a very good fit. However, when I compare the path or correlation coefficients, I see big differences between Standardized (STDYX) and non-standardized solutions in the correlation coefficients as well as their signficance levels.
why does this happen? Which solution should I choose?
 Linda K. Muthen posted on Wednesday, April 11, 2012 - 6:22 am
Raw and standardized coefficients have different sampling distributions. Because of this, their significances can differ. Raw and standardized coefficients are in a different metric. This is why their sizes vary. Which you should report depends on what is common practice in your field.
 Luo Wenshu posted on Tuesday, April 17, 2012 - 8:20 pm
Thank you very much, Linda.Could you answer me a follow-up question?
I am running path analysis (two level). does the standardized solution (STDYX) is the result of estimation by using correlation matrix for both within and between levels, rather than covariance matrix?
 Linda K. Muthen posted on Wednesday, April 18, 2012 - 6:49 am
No, standardization is done post analysis. See the STANDARDIZED option in the user's guide and Technical Appendix 3 on the website.
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: