Hi Everyone,
I'm doing some ARIMA forecasting and am finding the need to take the first difference of my variable of interest so I can get a stationary series. My variable of interest is hospital admissions. I have two questions:
1) If I have a numeric covariate, that is also time related, such as membership over time, do I need to take the first difference of that covariate?
2) If the answer to #1 is yes, how do I accomplish that in a PROC ARIMA statement?
Thank you!
proc arima data=arima_input3 plots=all;
identify var=admit_count (1)
crosscorr=(memberships)
nlag=53;
estimate q=2 input=(memberships);
forecast lead=106 interval=week id=admit_date out=results;
run;
It is usually a good practice to take the same diff of the crosscorr variables as the dependent var but it's up to the modeler to decide if diffing the crosscorr var is needed. You can accomplished it by adding the desirable diffs right after the crosscorr var (see below)
proc arima data=arima_input3 plots=all;
identify var=admit_count (1)
crosscorr=(memberships(1))
nlag=53;
estimate q=2 input=(memberships);
forecast lead=106 interval=week id=admit_date out=results;
run;
It is usually a good practice to take the same diff of the crosscorr variables as the dependent var but it's up to the modeler to decide if diffing the crosscorr var is needed. You can accomplished it by adding the desirable diffs right after the crosscorr var (see below)
proc arima data=arima_input3 plots=all;
identify var=admit_count (1)
crosscorr=(memberships(1))
nlag=53;
estimate q=2 input=(memberships);
forecast lead=106 interval=week id=admit_date out=results;
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 16. Read more here about why you should contribute and what is in it for you!
Learn how to run multiple linear regression models with and without interactions, presented by SAS user Alex Chaplin.
Find more tutorials on the SAS Users YouTube channel.