Observations removed because of missi... PreviousNext
Mplus Discussion > Missing Data Modeling >
Message/Author
 Trine Pedersen posted on Tuesday, July 05, 2011 - 1:18 pm
Hi.
We have replaced all of our missing values (regardless of type) with the number 999. In our code we write:

MISSING ARE ALL (999);

It seems like Mplus is now deleting ALL data of the respondents who somewhere in the line of questions has a missing value. This reduces our number of respondents/observations to a very small number. How can we remove ONLY the missing values, so that the respondents answers on all other questions are kept for the analysis?

Regards,
Trine & Helene
 Linda K. Muthen posted on Tuesday, July 05, 2011 - 1:50 pm
If you are using a current version of Mplus, the default is to use all obserations. In older versions, the default was listwise deletion. You can add TYPE=MISSING; to the ANALYSIS command if you are using an older version. If this does not help, send your output and license number to support@statmodel.com.
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: