No problem. I don't think you need sub-queries in this case, not unless there is more to the problem than you have posted.   All I'm using is a GROUP BY to summarise the data by customer ID. ... View more

seems fine. if you're unsure you could always create the indicator variables for S in a data step and then fit these in model and confirm the results correspond etc ... View more

you would want to sort the dataset in descending order first "proc sort; by descending efficiency; run;" and then there would be a number of ways to select the first 15 obs of this dataset, eg just count obs and "proc print data=xxx (where=(count le 15)); var efficiency; run;" ... View more