0

I am having difficulty turning unstandardized RMR estimates from AMOS software output in a SEM into standardized estimates to enable suitable interpretation. Can someone give me advice on where to start with this?

Kyle.
  • 1,550
  • 1
  • 11
  • 22
Bernard
  • 1
  • 1
  • 1
    I found these, don't know if it helps: http://www-01.ibm.com/support/docview.wss?uid=swg21477535 and http://www-01.ibm.com/support/docview.wss?uid=swg21480170 – Patrick Coulombe Mar 31 '14 at 16:35
  • This will be pretty tricky. The RMR is based on covariances, the SRMR on correlations. If you can persuade AMOS to analyze a correlation matrix, that will work. – Jeremy Miles Mar 31 '14 at 16:42
  • @PatrickCoulombe refers to the website which says "Note that the SRMR is undefined when there are missing values in the data." Every other SEM package (of which I am aware) will give SRMR with missing data. – Jeremy Miles Mar 31 '14 at 16:43

1 Answers1

1

In AMOS there is a plug-in that calculates SRMR for you. Across the top there is a "Plugins" drop down menu, and the SRMR plug-in is there.

Jay Wilkins
  • 11
  • 1