***********************************************************************
* Program:  C:\NHANES\CleanRecode_RecodeMissing.sas                   *
* Proposal: Recode values to missing                                  *                                            
***********************************************************************;
libname NH "C:\your_dir";

/*change the name of the directory folder to the location that you saved your downloaded dataset
 from the sample code and dataset downloads module: for example "c:\nhanes\data"*/



/*Data step to assign refusal, don't know as missing*/
Data demo_BP1;
        set NH.demo_BP;
      /*option 1: assign 7,9 as missing one by one*/
        if BPQ010 in (7,9) then BPQ010=.;
      /*option 2: assign 7,9 as missing by group - using array*/
        array _rdmiss bpq020 bpq070 bpq080 mcq160b--mcq160f;
        do over _rdmiss;
        if _rdmiss in (7, 9) then _rdmiss=.;
        end;
run;



/*Check the extent of missing data*/
Proc means data=NH.demo_BP N Nmiss min max;
where ridstatr=2 and ridageyr>=20; * interviewed and examined(ridstatr=2), adults age 20+;
	var BPQ010--BPQ100d MCQ160b--MCQ160f;  *blood pressure variables;
	Title "Check missing, min, max values for numeric variables";

Proc freq data=NH.demo_BP;
where ridstatr=2 and ridageyr>=20;
      table BPQ010--BPQ100d MCQ160b--MCQ160f/list missing;
      title 'Check frequency distribution for categorical variables';
run;