BookmarkSubscribeRSS Feed
🔒 This topic is solved and locked. Need further help from the community? Please sign in and ask a new question.
sasworker16
Calcite | Level 5

Hello,

 

I am running SAS 9.4 SAS/STAT 15.1 environment. 

 

I am trying to get similar results as

 

https://support.sas.com/resources/papers/proceedings17/SAS0462-2017.pdf 

 

in my dataset (~250,000 patient data, ~160 MB, about 250,000 rows and 40 columns) for 

 

1) ROC plot for selected time points

 

2) time-depednent integrated AUC plot with 95% confidence limits

 

with the following syntax

 

/*NOTE: a~kk are explanatory variables (n=37) for the binary outcome (0=no event, 1=event)*/

ods graphics on;
/*(1)*/ proc phreg data=a.data(overlay=individual)=roc rocoptions(at=1 2 3); model time*outcome(0)=a b c d e f g h i j k l n m o p q r s t u v w x y z aa bb cc dd ee ff gg hh ii jj kk; run; /*(2)*/ proc phreg data=a.data plots=auc rocoptions(method=ipcw(cl seed=1234) iauc); model time*outcome(0)=a b c d e f g h i j k l n m o p q r s t u v w x y z aa bb cc dd ee ff gg hh ii jj kk; run;

I also increased the MEMSIZE in the config file to 12G. 

 

However, it is running forever and not showing any graphs and only the following message shows up in the Log Window. 

 

NOTE: Convergence criterion (GCONV=1E-8) satisfied.

 

How do I fix this problem and get the graphs I need? It works with fewer variables in the model (e.g only with the four variables: a, b, c, d)

 

Do I have too many variables (e.g 37 variables) in the model?

 

Any help or suggestions would be appreciated.

 

Thank you. 

1 ACCEPTED SOLUTION

Accepted Solutions
Reeza
Super User
What happens if you run it with all variables, but a smaller sample, say 50,000 rows? And or, keep adding variables and find out which breaks it. I'm assuming some of those are dummy variables since I see no CLASS statement?

View solution in original post

2 REPLIES 2
PaigeMiller
Diamond | Level 26

How long is "forever"??

 

It may be possible that plotting with this many variables and this many observations and asking for many different plots overloads the capabilities of your computer.

--
Paige Miller
Reeza
Super User
What happens if you run it with all variables, but a smaller sample, say 50,000 rows? And or, keep adding variables and find out which breaks it. I'm assuming some of those are dummy variables since I see no CLASS statement?

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!
How to Concatenate Values

Learn how use the CAT functions in SAS to join values from multiple variables into a single value.

Find more tutorials on the SAS Users YouTube channel.

Click image to register for webinarClick image to register for webinar

Classroom Training Available!

Select SAS Training centers are offering in-person courses. View upcoming courses for:

View all other training opportunities.

Discussion stats
  • 2 replies
  • 507 views
  • 0 likes
  • 3 in conversation