Number of observations PreviousNext
Mplus Discussion > Confirmatory Factor Analysis >
Message/Author
 Ioanna Vrouva posted on Monday, March 09, 2009 - 9:12 am
I would be very grateful for your reply.
I have an SPSS datafile, with 722 cases and missing values coded as -1.
I save the spss file into a FIXED ASCII file as usual and then run the (simplified) syntax:

TITLE: example
DATA: FILE IS example.dat;
VARIABLE: NAMES ARE yy yy2 yy3 xx xx2 xx3;
USEVARIABLES ARE yy yy2 yy3 xx xx2 xx3;
CATEGORICAL ARE yy yy2 yy3 xx xx2 xx3;
MISSING ARE all (-1);
MODEL: f1 BY yy yy2 yy3;
f2 BY xx xx2 xx3;

THE PROBLEM is that in the OUTPUT the Number of observations is 720 instead of 722. I repeat saving the spss file into different datafiles (with different names) but the same error occurs.
Any advice about why this may happen would be greatly appreciated
Thanks very much
Ioanna vrouva
 Linda K. Muthen posted on Monday, March 09, 2009 - 10:18 am
SPSS saves some missing values as blanks. If you have blanks in the data set and are reading it with free format, the data will not be read correctly. If you cannot see the problem, please send the input, data, output, and your license number to support@statmodel.com.
 Ioanna Vrouva posted on Monday, March 09, 2009 - 12:35 pm
Thank you very much, it did solve the problem. There were variables in the datafile (not used in the analyses) with 2 blanks so after fixing them all observations were taken into account.
Thanks again
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: