SPSSX Discussion

vastorcases and mixed models

Classic

List

Threaded

4 messages Options

jlukewood

vastorcases and mixed models

Does anyone know if converting clustered data to vastorcases is required to run a mixed model?

Bruce Weaver

Re: vastorcases and mixed models

Administrator

The MIXED procedure requires one observation per row in the data file. So if your data are currently in a WIDE format, then yes, you need to restructure. Obviously, you'll need a variable that indicates which cluster each data point belongs to.

jlukewood wrote

Does anyone know if converting clustered data to vastorcases is required to run a mixed model?

--
Bruce Weaver
bweaver@lakeheadu.ca
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

PLEASE NOTE THE FOLLOWING:
1. My Hotmail account is not monitored regularly. To send me an e-mail, please use the address shown above.
2. The SPSSX Discussion forum on Nabble is no longer linked to the SPSSX-L listserv administered by UGA (https://listserv.uga.edu/).

jlukewood

Re: vastorcases and mixed models

Is this still the case if the data I have are students (16,000), clustered within colleges (112), with a college ID variable and for data collected at only one point in time? (e.g., not looking for longitudinal statements)?

Bruce Weaver

Re: vastorcases and mixed models

Administrator

Yes.

jlukewood wrote

Is this still the case if the data I have are students (16,000), clustered within colleges (112), with a college ID variable and for data collected at only one point in time? (e.g., not looking for longitudinal statements)?