I ran the following codes to graphically show the predicted probabilities of y
(binary) vs. x1
(continuous) at different values of x2
(continuous).
proc logistic data=data;
model y(event='1') = x1 | x2;
store logiMod;
run;
title "Predicted probabilities";
proc plm source=logiMod;
effectplot slicefit(x=x1 sliceby=x2=0 to 30 by 5);
run;
These codes give me the graph for the whole range of x1. But I want to show this graph for a specified range of x1 (say, for 0-20 with an increment of 2 for grids) without changing my main model. How can I get that? Can anyone demostrate any alternative way to produce a similar graph if such an option is not available in proc plm?
For more flexibility, you could skip proc plm and do your own scoring. For example:
data heart;
set sashelp.heart;
alive = missing(ageAtDeath);
run;
data graphValues;
do smoking = 0, 10, 20, 30;
do systolic = 120 to 180;
output;
end;
end;
label
smoking="Cigarettes per day"
systolic="Systolic blood pressure";
run;
proc logistic data=heart;
model alive = systolic smoking;
score data=graphValues out=graphScores;
run;
proc sgplot data=graphScores;
series x=systolic y=p_0 / group=smoking lineattrs=(pattern=solid);
run;
For more flexibility, you could skip proc plm and do your own scoring. For example:
data heart;
set sashelp.heart;
alive = missing(ageAtDeath);
run;
data graphValues;
do smoking = 0, 10, 20, 30;
do systolic = 120 to 180;
output;
end;
end;
label
smoking="Cigarettes per day"
systolic="Systolic blood pressure";
run;
proc logistic data=heart;
model alive = systolic smoking;
score data=graphValues out=graphScores;
run;
proc sgplot data=graphScores;
series x=systolic y=p_0 / group=smoking lineattrs=(pattern=solid);
run;
Are you ready for the spotlight? We're accepting content ideas for SAS Innovate 2025 to be held May 6-9 in Orlando, FL. The call is open until September 25. Read more here about why you should contribute and what is in it for you!
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.