I was trying to run this code on SAS Studio University Edition 9.4 on my hp desktop, which is a few years old:
TITLE 'Unstructured Covariates'; /* Question 5.1.5, but it won't run properly */
PROC MIXED DATA=Long.cholesterol_data METHOD=reml;
CLASS GROUP ID;
MODEL cholesterol = GROUP / S ddfm=kr;
repeated ID / subject=ID TYPE=UN;
RUN;
It only partially ran, and I got an error message saying that SAS is out of memory (I'm sorry, I didn't have the foresight to take a screenshot at the time. I kept trying to run the code, and then I did an ACPI shutdown and rebooted my computer. It didn't work).
Now, no code will run except LIBNAME statements on my desktop AND on my new Surface Pro laptop (only a couple months old). Everyone keeps saying it's a RAM or storage issue, but on my desktop, my RAM has 7 GB free and my hard drive has 200 GB free, and, like I said, it has affected my new laptop as well.
Do I need to uninstall and reinstall Oracle VM VirtualBox or SAS? On both computers?
I have also attached the data set I was using so you can see the variables I was working with.
Yeah, I probably should have done PROC SORT first. However, it seems like there was an issue with the data file because when I removed it from my folder, I was able to run code again. Thanks for your help!
I'm not currently in a position to check your source data (and I know nothing about proc mixed!), but a generic response to this sort of problem would be to presort the source by group and id, then replace the class statement with
by group id;
It's worth a try.
The reason this may make a difference is that SAS knows the source is in this order, and doesn't need to load all the data into memory to work out all the different combinations of the two variables.
Yeah, I probably should have done PROC SORT first. However, it seems like there was an issue with the data file because when I removed it from my folder, I was able to run code again. Thanks for your help!
April 27 – 30 | Gaylord Texan | Grapevine, Texas
Walk in ready to learn. Walk out ready to deliver. This is the data and AI conference you can't afford to miss.
Register now and lock in 2025 pricing—just $495!
Get started using SAS Studio to write, run and debug your SAS programs.
Find more tutorials on the SAS Users YouTube channel.
Ready to level-up your skills? Choose your own adventure.