I am creating a scatter plot where I want upper and and lower limits that use the code below. The issue is that when I try to define the variables something goes wrong when putting the standard deviation in the statement. An error comes up saying that I don't have enough arguments. How do I fix this?
DATA WORK.Case_Control;
SET Epid.case_control_analysis;
Diff = BMI_GS - BMI_SR;
UpperLimit = MEAN(Diff) + 1.96*STD(diff);
LowerLimit = MEAN (Diff) - 1.96*STD(diff);
Bias = MEAN(diff);
proc means data = WORK.Case_Control mean std;
Var Diff;
run;
Proc SGplot data = WORK.Case_Control;
scatter X = BMI_GS Y = Diff;
label BMI_GS = "Gold-Standard BMI Measure";
label Diff = "Gold-Standard - Self-Report";
refline 0 / transparency = 0.1 lineattrs=(color=black pattern =1 thickness =3);
refline UpperLimit / transparency = 0.1 Label = ('Upper Limit of Agreement') lineattrs=(color=red pattern=2 thickness =3);
refline LowerLimit / transparency = 0.1 Label = ('Lower Limit of Agreement') lineattrs=(color=red pattern=2 thickness =3);
refline Bias / transparency = 0.1 Label = ('Bias') lineattrs=(color=red thickness =3);
run;
You should define dataset case_control as:
proc sql;
create table Case_Control as
select
BMI_GS, BMI_SR,
BMI_GS - BMI_SR as diff,
mean(BMI_GS - BMI_SR) as bias,
mean(BMI_GS - BMI_SR) - 1.96*std(BMI_GS - BMI_SR) as lowerLimit,
mean(BMI_GS - BMI_SR) + 1.96*std(BMI_GS - BMI_SR) as upperLimit
from Epid.case_control_analysis;
quit;
You should define dataset case_control as:
proc sql;
create table Case_Control as
select
BMI_GS, BMI_SR,
BMI_GS - BMI_SR as diff,
mean(BMI_GS - BMI_SR) as bias,
mean(BMI_GS - BMI_SR) - 1.96*std(BMI_GS - BMI_SR) as lowerLimit,
mean(BMI_GS - BMI_SR) + 1.96*std(BMI_GS - BMI_SR) as upperLimit
from Epid.case_control_analysis;
quit;
Awesome, I finally got that to work.
April 27 – 30 | Gaylord Texan | Grapevine, Texas
Walk in ready to learn. Walk out ready to deliver. This is the data and AI conference you can't afford to miss.
Register now and save with the early bird rate—just $795!
Get started using SAS Studio to write, run and debug your SAS programs.
Find more tutorials on the SAS Users YouTube channel.
Ready to level-up your skills? Choose your own adventure.