*----------------------------------------------------------------*
| Purpose: To list the upper and lower n% of values              |
| Arguments: DSN     - Data set name (one- or two-level          |
|            VAR     - Variable to test                          |
|            PERCENT - Upper and lower n%                        |
|            IDVAR   - ID variable                               |
| Example: %HI_LOW_P(CLEAN.PATIENTS,SBP,20,PATNO)                |
*----------------------------------------------------------------*;

%MACRO HI_LOW_P(DSN,VAR,PERCENT,IDVAR);
   ***Compute number of groups for PROC RANK;
   %LET GRP = %SYSEVALF(100 / &PERCENT,FLOOR); 
   ***Value of the highest GROUP from PROC RANK, equal to the
      number of groups - 1;
   %LET TOP = %EVAL(&GRP - 1); 

   PROC FORMAT; 
      VALUE RNK 0='Low' &TOP='High';
   RUN;

   PROC RANK DATA=&DSN OUT=NEW GROUPS=&GRP; 
      VAR &VAR;
      RANKS RANGE; 
   RUN;

   ***Sort and keep top and bottom n%;
   PROC SORT DATA=NEW (WHERE=(RANGE IN (0,&TOP))); 
      BY  &VAR;
   RUN;

   ***Produce the report;
   PROC PRINT DATA=NEW; 
      TITLE "Upper and Lower &PERCENT.% Values for %UPCASE(&VAR)";
      ID &IDVAR;
      VAR RANGE &VAR;
      FORMAT RANGE RNK.;
   RUN;

   PROC DATASETS LIBRARY=WORK NOLIST; 
      DELETE NEW;
   RUN;
   QUIT;

%MEND HI_LOW_P;