Thanks, I will surely try it.  ... View more

Yes, although we do not have directionality with causal mediation (but maybe there is - look at all the minus signs in the table!). It is tempting to say that part of the reason why individuals of minority status have lower test scores is because of lower income, but that would need further exploration. Right now, it would probably be more accurate to conclude that race has an effect on test scores partly due to differences in income. ... View more

  proc freq data=have noprint; table id*level/ out=durations sparse missing; run; data want; set durations; time_in_period = count/2; run; *transpose to desired structure; Assume you mean by period instead of level (level has 8 categories 0-7, Period has 7, P1-P7). SInce you keep saying it has 7, I assume you're referring to Period not level.  See if the above gives you the answers you want. If so let us know and we can show you how to transpose and remerge it back into the main data set if you really want the structure you've shown.    ... View more

You can do this by creating formats. This should help https://blogs.sas.com/content/iml/2016/08/08/sas-formats-bin-numerical-variables.html  ... View more

Not sure if this is what you are looking for. The code below goes out and grabs all the files in a directory and creates variable from the file names. I included a link to the External File Functions.   /* External File Functions https://go.documentation.sas.com/?cdcId=pgmsascdc&cdcVersion=9.4_3.5&docsetId=allprodsle&docsetTarget=syntaxByCategory-function.htm&locale=en#n1xjxmfjlyclzjn1hyatp8m76hr7 */ filename myDir "\Some\folder\some\where" ; data want ; /* get a directory handle for the directory */ dirRC=dopen("myDir") ; put dirRC= ; /* get the number of files in the directory */ dNum=dnum(dirRC) ; put dNum= ; /* loop through the files */ do i=1 to dnum ; /* get the filename */ filename=dread(dirRC,i) ; put filename= ; /* now do whatever you want with the filename */ var1=substr(filename,1,4) ; output ; end ; run ; ... View more

Keep it simple:   data counts; do n = 1 by 1 until(last.count); set have; by count notsorted; end; if count = 5 then do; do bin = 1 to 141 by 10; if n >= bin then output; end; end; keep n bin; run; proc sql; create table want as select bin, count(n) as nbSequences, sum(n) as nb5Counts from counts group by bin; quit; proc print data=want noobs; run; nb bin Sequences nb5Counts 1 5 155 11 2 135 21 2 135 31 2 135 41 2 135 51 2 135 61 1 81 71 1 81 81 1 81 ... View more