Hi,
I'm generating a plot of predicted probabilities with CI's bands using proc logistic. The plot displays predicted probabilities vs. x1 holding values of x2-x5 at constant levels that I've specified. The default title is long and ugly and I would like to completely remove the title and just have leave the title blank. Do you know how to do that?
Here is my code:
ods listing gpath='my directory';
ods graphics on/reset=all border=off imagefmt=tiff imagename='Name' width=6 in height=6 in;
proc logistic data=datax (where=(y>.z)) plots(only)=(effect(at(x2=0 x3=0 x4=66 x5=1) yrange=(0,0.1) showobs=no)) descending;
model y=x1 x2 x3 x4 x5;
run;
ods graphics off;
ods listing close;
Yes, SAS supplies the %GrTitle macro for exactly this purpose. By coincidence, the documentation for the %GrTitle macro uses PROC LOGISTIC, although it is a different graph than yours. Give it a go and see if you can follow the documentation example.
Yes, SAS supplies the %GrTitle macro for exactly this purpose. By coincidence, the documentation for the %GrTitle macro uses PROC LOGISTIC, although it is a different graph than yours. Give it a go and see if you can follow the documentation example.
Thanks for the help! My first attempt with the %grtitle didn't work, as the output to the log didn't contain a list of macro variables to modify, it instead just mentioned that there was a "link" statement to a different template, one that was not the template name uncovered by "ods trace on". When I repeated the %grtitle call using the template name of the template that was linked to, I did get the names of macro variables to modify and now I have successfully removed the title. Thanks, Rick!
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!Use this tutorial as a handy guide to weigh the pros and cons of these commonly used machine learning algorithms.
Find more tutorials on the SAS Users YouTube channel.