SAS - drop variables with a percentage missing

SAS_drop_variables_missing.sas

%macro drop_missing_pct(input_dsn = , output_dsn=, pct = , id_vars=);

*input_dsn = input data set name;
*output_dsn = output data set name;
*pct = missing percent, variables with a percentage of missing above this value are dropped;
*id_vars = space delimited list of variables that you do not want to include in the analysis such as ID variables;


*create format for missing;
proc format;
    value $ missfmt ' '="Missing" other="Not Missing";
    value nmissfmt .="Missing" other="Not Missing";
run;

*Proc freq to count missing/non missing;
ods select none;
*turns off the output so the results do not get too messy;
ods table onewayfreqs=temp;

proc freq data=&INPUT_DSN. (drop = &ID_Vars);
    table _all_ / missing;
    format _numeric_ nmissfmt. _character_ $missfmt.;
run;


ods select all;
*Format and organize output;

data long;
    length variable $32. variable_value $50.;
    set temp;
    Variable=scan(table, 2);
    Variable_Value=strip(trim(vvaluex(variable)));
    presentation=catt(frequency, " (", trim(put(percent/100, percent7.1)), ")");
    keep variable variable_value frequency percent cum: presentation;
    label variable='Variable' variable_value='Variable Value';
run;

*not required for display purposes;
proc sort data=long;
    by variable;
run;

*select variables more than x% missing;
proc sql noprint;
select variable into :drop_var_list separated by " "
from long where variable_value = 'Missing' and percent > &pct;
quit;

*Drop variables;
data &output_dsn;
set &input_dsn;
drop &drop_var_list;
run;

*clean up;
*uncomment after testing;
/* proc sql; */
/* drop table long; */
/* drop table temp; */
/* quit; */

%mend;

***************************************************************************************************
*Example Usage
***************************************************************************************************;

data class;
    set sashelp.class;

    if age=14 then
        call missing(height, weight, sex);

    if name='Alfred' then
        call missing(sex, age, height);
    label age="Fancy Age Label";
run;


%drop_missing_pct(input_dsn = class, output_dsn = want, pct = 20, id_vars = Name);



*check output;
proc contents data=want;
run;