BookmarkSubscribeRSS Feed
annamariaclelia
Calcite | Level 5

I'm using a multinomial logit model to study a large dataset, approximately 700.000 observations. In particular I have 700.000 observations divided in 23 classes at time 1, and each one evolves in the same or a different class of this at time 2. So, with proc logistic with link multilogit I'm trying to estimate the probability that an observation in the class i at time 1 goes to class j at time 2( also j=i is accetable). Here is the code:

 

PROC SORT DATA=Finalall OUT=Dieci_undici ; 

BY _2010;

RUN ;


proc logistic data=Dieci_undici; by _2010; 

 model _2011=SHP_AREA / link=glogit;

quit;

 

And it works. Buf if I add this line:  

 

output pred = predicted predprobs = i;

 

Then I have the following problem :

 

"OUT OF RESOURCES Select"

 

-R. Retry

-N Tell procedure/DATA step no more resources

-C Cancel Submitted Statement

- T. Terminate SAS

 

What is wrong?

 

Thank you very much for your help.

 

 

1 REPLY 1
Kurt_Bremser
Super User

You're most probably running out of space in WORK. Clean up there before running the proc logistic, or redirect the output to another library that sits on a different physical location.

Ready to join fellow brilliant minds for the SAS Hackathon?

Build your skills. Make connections. Enjoy creative freedom. Maybe change the world. Registration is now open through August 30th. Visit the SAS Hackathon homepage.

Register today!
What is ANOVA?

ANOVA, or Analysis Of Variance, is used to compare the averages or means of two or more populations to better understand how they differ. Watch this tutorial for more.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 1 reply
  • 1644 views
  • 0 likes
  • 2 in conversation