How do I get the crosscorr table from PROC ARIMA

[somebody]

I am computing the cross correlation of 2 variables. How do I get the results in a dataset? I had a look at this link I think I have to use CrossCorrGraph but got an error message.

https://documentation.sas.com/?docsetId=etsug&docsetTarget=etsug_arima_details53.htm&docsetVersion=1...

here is my code:

proc arima data=sample; 
	by permno;
	identify var=r crosscorr=vol_change nlag=10 nomiss;
	ods output cc=CrossCorrGraph;
run;quit;

[FreelanceReinh]

Hi @somebody,

The syntax is

ODS OUTPUT output-object-specification=data-set;

i.e., in your example:

ods output CrossCorrGraph=cc;

[somebody]

I tried that but got the following message:

WARNING: Output 'CrossCorrGraph' was not created.  
Make sure that the output object name, label, or path is spelled correctly.  
Also, verify that the appropriate procedure options are used to produce the requested output object.  
For example, verify that the NOPRINT option is not used.

[FreelanceReinh]

This warning message confirms that the syntax of the ODS OUTPUT statement is now correct and indicates that a different issue prevents the creation of the desired table. I'm sorry I don't have a SAS/ETS license nor any experience with this module, so can't help you much with PROC ARIMA. My next steps in the investigation would be:

1. Is the graph (whose data the ODS table CrossCorrGraph would contain) created at all?
2. Any other graph (see ODS Graph Names)?
3. After submitting ods graphics on; ?
4. Does the procedure output (or other log messages) give any hint about issues with the input dataset?
5. Temporarily simplify the code: omit the NOMISS option, omit the BY statement or replace it with a WHERE statement restricting the dataset to one of the BY groups.
6. Use a working example, e.g., from the documentation (Example 7.3 should be suitable) as a basis, add your ODS OUTPUT statement and, once this creates the CrossCorrGraph table, modify the code and the input dataset step by step so as to make it more and more similar to your actual code and data. Then you would see what change stops the creation of that table.

If all the above doesn't help, I recommend that you open a new thread in the SAS Forecasting and Econometrics subforum.

Good luck!