Thx so much. Will do! ... View more

Check that your data sets are mentioned in the proper order:   set a_dataset (in=in1)    another_dataset (in=in2);   The first data set should be the one with multiple records per ticker.   If that's not the issue, I would need to see a few lines of data that are causing the problem.   Also note, if both data sets contain the same date value, this program selects the matching date (not an earlier date).  That can be changed if necessary. ... View more

Hi:   If they are SAS date variables, you can just subtract them and then, if you want to get the absolute value, without a negative sign (since depending on your 2 numbers, you might get a negative DIFF), then you can just use the ABS function. cynthia ... View more

It would be better if you post some data and output. I think you could start with the following code.   data want;  set date cusid;  by date; run; ... View more

To expand on @ballardw's reply, the statistics that you are looking for are called "parameter estimates." That should help you with internet searches.   In addition to using the OUTEST= option, you should add the NOPRINT option to the PROC REG statement so that the screen is not filled with hundreds of tables/graphs that you don't need to see. The following statements create an output data set called ParamEst that contains all parameter estimates. You can use a WHERE clause to restrict the output it you only want the estimates for s_score.   proc reg data=b5 outest=ParamEst noprint; by date; model mtb = size roa s_score / adjrsq; quit; ... View more

Add   FitStatistics=f1   to your ODS OUTPUT statement. ... View more

Get a copy of SAS for Mixed Models, 2nd ed. by Littell et al.  It will have the examples (and some theory) on how to address this.   Steve Denham ... View more

I would not migrate to Windows 10 in a production environment at the moment. It's much too young for that. Keep in mind that it usually takes the equivalent of two major service packs until a Windows version becomes stable and usable. ... View more

Hi,   I just made a small assumption on how your data would look like given your request! First I used a transpose (1 line per company per year, with an entry for each month). Then I used a data step icw array-function to determine the yearly return:   data input (drop = i); format company $13.; do i = 1 to 12; year = 2016; month = i; company = 'A'; return = i/100; output; company = 'B'; return = (i+1)/100; output; end; run; proc sort data=input out=sortedInput; by year company month; run; proc transpose date=sortedInput out=tInput prefix=M; by company year; id month; run; data output (drop=i); set tInput; array allMonths(12) M1-M12; yearReturn = 1; do i = 1 to dim(allMonths); yearReturn = yearReturn*(1+allMonths[i]); end; yearReturn = yearReturn -1; run;   Hope this helps.   John ... View more