Save data PreviousNext
Mplus Discussion > Structural Equation Modeling >
 Daniel posted on Wednesday, May 25, 2005 - 12:09 pm
I have a question regarding the save data command. When I save data to a .sav file, and then pick up my data in excel, on its way to SAS, I lose once case, such that my new N = N-1 from the Mplus file. Is there something I should do to fix this problem?
 Linda K. Muthen posted on Wednesday, May 25, 2005 - 3:04 pm
I just saved data and opened the saved data in Excel and got the correct number of cases in Excel. Are you doing this differently? If so, how?
 Daniel posted on Thursday, May 26, 2005 - 4:57 am
Ok, the problem is when I import the data into SAS from excel, after saving the Mplus data into excel. Thanks.
 Daniel posted on Thursday, May 26, 2005 - 5:08 am
I am having a hard time figuring out how to import the Mplus data directly into SAS; that's why I go through the two-stage process of Mplus-excel-SAS. How do I format my data so that it goes directly into SAS?
 Linda K. Muthen posted on Thursday, May 26, 2005 - 5:27 am
It must have something to do with SAS or Excel because there are the correct number of observations in the saved data and Mplus is not part of the process after that. Perhaps SAS would have an explanation. Can't SAS just read an ASCII file? And that save it as a SAS file. Is it necessary to go through Excel? I'm not that familiar with SAS.
 Daniel posted on Thursday, May 26, 2005 - 6:43 am
I'm working on learning how to do that. I'll let you know as soon as I find out.
 Rebecca Müller posted on Monday, April 03, 2017 - 3:51 am

I'm trying to create two latent variables with two CFAs and further to save these two new variables in a new datafile.
I'm doing this, beceaus I want to center (grandmean) these two latent variables in a next step and calculate an interaction/moderation between them.

I use the SAVEDATA command and I always get an error:

*** WARNING in SAVEDATA command
(Err#: 9)
Error opening data save file:
Data will not be saved.

How can I fix this error or is there another option to center two latent variables in one step?

Thank you for help.

 Bengt O. Muthen posted on Monday, April 03, 2017 - 8:53 am
Typically, latent variables have mean zero so no centering is needed. If this doesn't help, send your output to Support along with your license number.
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