Subset question

[mcmaxwell]

Hello,

I would like to run a Chi squared test on some data I collected. Here is an example of my dataset: 

c_ses3 has two levels (cPLTL or non-cPLTL) and refers to whether a student participated in a teaching intervention or not. ABC has two levels (ABC or DFW) and refers to a students final grade. Tutoring refers to how many tutoring sessions a student attended and ranges from 0 to 12. ST_c has 6 levels (0-1, 1-2, 2-3, 3-4, 4-5, 6+) and represents how much time a student spent studying weekly.

I used the code below to do the chi squared test:

/** get contingency table and run chisq**/     
proc freq data=all;    
	title "cPLTL 2-3h ST vs. non-cPLTL 3-4h ST";    
	table c_ses3 * ABC / chisq expected nopercent nocol norow;     
	where tutoring between 0 and 3;    
	run;    

As you can see, I am comparing the ABC rates of cPLTL and non-cPLTL groups, and I am only using students who attended 0, 1, 2, or 3 tutoring sessions. 

Here is my problem: I would like to specifically compare cPLTL students who studied 2-3 hours with non-cPLTL students who studied 3-4 hours. I am not sure how to write the code to subset the ST_c variable because the way it should be subsetted depends on the c_ses3 variable. Is there a way to do this? Or a different way I could organize my data? 

Thank you in advance!!!

[Tom · Accepted solution]

Sounds like you could do that with just a different WHERE clause.

where (c_ses3='cPLTL' and tutoring between 2 and 3)
   or (c_ses3='non-cPLTL' and tutoring between 3 and 4)
;