Hi. My task is to analyze a very simple and straightforward cancer registry. My output was significantly different after changing the option, even though in my opinion it was just for display purposes. Below I have included both code and their outputs for your reference. Could you please explain what happened and which version is better? I really appreciate your time and help.
proc lifetest data=registry atrisk plot=(survival (atrisk=0 to 5 by 1 atrisktickonly))
outsurv=ci95 maxtime=5 timelist=(0 to 5 by 1) reduceout;
time survyr*vital(1);
strata rgroup1/ test=all;
label survyr ='Time in years' rgroup1="race";
run;
proc lifetest data=registry atrisk plot=(survival ( test atrisk=0 to 5 by 1 atrisktickonly outside))
timelist=(0 to 5 by 1) outsurv=ci95 maxtime=5 timelist=(0 to 5 by 1) reduceout;
time survyr*vital(1);
strata rgroup1/ test=all;
label survyr ='Time in years' rgroup1="race";
run;
Hi @oddsratio,
I can reproduce the issue using SASHELP sample data (as in https://documentation.sas.com/doc/en/pgmsascdc/9.4_3.3/statug/statug_code_liftex2.htm), but only after modifying the template as described in Customizing the Kaplan-Meier Survival Plot. Specifically, I had to set the VIEWMIN= option to 0.5 in order to get a y-axis similar to that in your plots:
%ProvideSurvivalMacros %let yOptions = linearopts=(viewmin=0.5 viewmax=1); %CompileSurvivalTemplates
Did you modify the template in a similar way? Using the default viewmin=0 (or a sufficiently small value >0) should resolve the issue.
Hi @oddsratio,
I can reproduce the issue using SASHELP sample data (as in https://documentation.sas.com/doc/en/pgmsascdc/9.4_3.3/statug/statug_code_liftex2.htm), but only after modifying the template as described in Customizing the Kaplan-Meier Survival Plot. Specifically, I had to set the VIEWMIN= option to 0.5 in order to get a y-axis similar to that in your plots:
%ProvideSurvivalMacros %let yOptions = linearopts=(viewmin=0.5 viewmax=1); %CompileSurvivalTemplates
Did you modify the template in a similar way? Using the default viewmin=0 (or a sufficiently small value >0) should resolve the issue.
Thank you so much for helping me out. You are right! By using the default setting view in=0, the difference was resolved.
It's finally time to hack! Remember to visit the SAS Hacker's Hub regularly for news and updates.
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.
Ready to level-up your skills? Choose your own adventure.