Discrepancy with missing are all command PreviousNext
Mplus Discussion > Missing Data Modeling >
Message/Author
 Brian N. Phillips posted on Friday, June 09, 2017 - 2:07 pm
I am a newer Mplus user and can't figure out what is going on with my analysis.

I have 330 cases without any missing data on the measured variables.

When I include the following command code anyway "MISSING ARE all (-99);" it drastically changes the results of my chi-square goodness of fit test.

I would like to not use the command, but I am hesitating since it seems to me that I should get the same results with or without that command.

Is there an explanation for the discrepancy? Thank you!
 Bengt O. Muthen posted on Friday, June 09, 2017 - 2:25 pm
First, ask for Patterns in the Output command to check your missing data status when using the MISSING statement. Perhaps some of your variables have legitimate values of -99.

If that doesn't help, send input, output, data and license number to Support.
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: