*----------------------------------------------------------------*
| Purpose: To list N highest and lowest values (approximately)   |
| Arguments: DSN     - Data set name (one- or two-level          |
|            VAR     - Variable to test                          |
|            N       - Number of highest and lowest values       |
|            IDVAR   - ID variable                               |
| Example: %HI_LOW_N(CLEAN.PATIENTS,SBP,10,PATNO)                |
*----------------------------------------------------------------*;
%MACRO HI_LOW_N(DSN,VAR,N,IDVAR);
   ***Find the number of observations in data set;
   %LET DSID = %SYSFUNC(OPEN(&DSN)); 
   %LET N_OBS = %SYSFUNC(ATTRN(&DSID,NOBS));
   %LET RETURN = %SYSFUNC(CLOSE(&DSID));

   ***Compute number of groups, from N and N_OBS;
   %LET GRP = %SYSEVALF(&N_OBS / &N,FLOOR); 
   ***Continue as in the macro based on percents;
   %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 "Approximate Highest And Lowest &N 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_N;