Add the Person Identifier (NRPID) to the 2000-01 Migrant Follow-Up data

******************************************************************************
Attach NRPID to the 2000 Migrant Follow-Up Individual-Level Data File
   1. Select ONLY 2000 Migrants in the PERSONID Data File
   2. Restructure MIGRANT00 into "Child" File,
      as 14 Migrants are in Migrant Follow-Up TWICE
   3. Match SMIGRANT00B to the MINDIV00 Data File

Input data: /nangrong/personid.X01
            /nangrong/2000/mindiv00.02
*****************************************************************************;

libname in1 xport '/nangrong/personid.X01';
libname in2 xport '/nangrong/2000/mindiv00.02';

***************************************************************************
*  Attach NRPID to the 2000 Migrant Follow-Up Individual-Level Data File  *
***************************************************************************;

* 1. Select ONLY 2000 Migrants in the PERSONID Data File *
-----------------------------------------------------------;
data migrant00;
  set in1.personid(keep=MID00 MIGTYPE MCEP00 MID00B MIGTYPEB MCEP00B NRPID);

  if (MID00 ne ' ');

*** Rename Variables ***;

rename
MID00=MID00A
MIGTYPE=MIGTYPEA
MCEP00=MCEP00A
;

run;

* 2. Restructure MIGRANT00 into "Child" File,
     as 14 Migrants are in Migrant Follow-Up TWICE *
-----------------------------------------------------;
data migrant00b;
  set migrant00;
  length MID00 $ 11 MIGTYPE $ 4 MCEP00 $ 2;

  keep MID00 MIGTYPE MCEP00 NRPID;

  array m3 {2} MID00A MID00B;
  array m4 {2} MIGTYPEA MIGTYPEB;
  array m5 {2} MCEP00A MCEP00B;

  do i=1 to 2;
   MID00=m3{i};
   MIGTYPE=m4{i};
   MCEP00=m5{i};
   if MID00 ne ' ' then output;
  end;

run;

*** Sort MIGRANT00B by MID00 MIGTYPE MCEP00 ***;

proc sort data=migrant00b out=smigrant00b nodupkey;
  by MID00 MIGTYPE MCEP00;
run;

* 3. Match SMIGRANT00B to the MINDIV00 Data File *
--------------------------------------------------------;
data mindiv00_nrpid notin_mindiv00 notin_migrant00b;
  merge smigrant00b(in=a)
        in8.mindiv00(in=b);
  by MID00 MIGTYPE MCEP00;

  if a=1 and b=1 then output mindiv00_nrpid;
  if a=1 and b=0 then output notin_mindiv00;
  if a=0 and b=1 then output notin_migrant00b;

run;

*** Check for Duplicates on NRPID in MINDIV00_NRPID (SHOULD HAVE 14!) ***;

proc sort data=mindiv00_nrpid out=smindiv00_nrpid nodupkey;
  by NRPID;
run;

375        ***************************************************************************
376        *  Attach NRPID to the 2000 Migrant Follow-Up Individual-Level Data File  *
377        ***************************************************************************;
378        
379        * 1. Select ONLY 2000 Migrants in the PERSONID Data File *
380        -----------------------------------------------------------;
381        data migrant00;
382          set in1.personid(keep=MID00 MIGTYPE MCEP00 MID00B MIGTYPEB MCEP00B NRPID);
383        
384          if (MID00 ne ' ');
385        
386        *** Rename Variables ***;
387        
388        rename
389        MID00=MID00A
390        MIGTYPE=MIGTYPEA
391        MCEP00=MCEP00A
392        ;
393        
394        run;

NOTE: There were 57416 observations read from the data set IN1.PERSONID.
NOTE: The data set WORK.MIGRANT00 has 5412 observations and 7 variables.
NOTE: DATA statement used:
      real time           0.87 seconds
      cpu time            0.83 seconds
      
395        
396        * 2. Restructure MIGRANT00 into "Child" File,
                as 14 Migrants are in Migrant Follow-Up TWICE *
397        -----------------------------------------------------;
398        data migrant00b;
399          set migrant00;
400          length MID00 $ 11 MIGTYPE $ 4 MCEP00 $ 2;
401        
402          keep MID00 MIGTYPE MCEP00 NRPID;
403        
404          array m3 {2} MID00A MID00B;
405          array m4 {2} MIGTYPEA MIGTYPEB;
406          array m5 {2} MCEP00A MCEP00B;
407        
408          do i=1 to 2;
409           MID00=m3{i};
410           MIGTYPE=m4{i};
411           MCEP00=m5{i};
412           if MID00 ne ' ' then output;
413          end;
414        
415        run;

NOTE: There were 5412 observations read from the data set WORK.MIGRANT00.
NOTE: The data set WORK.MIGRANT00B has 5426 observations and 4 variables.
NOTE: DATA statement used:
      real time           0.13 seconds
      cpu time            0.08 seconds   

416        
417        *** Sort MIGRANT00B by MID00 MIGTYPE MCEP00 ***;
418        
419        proc sort data=migrant00b out=smigrant00b nodupkey;
420          by MID00 MIGTYPE MCEP00;
421        run;
 
NOTE: 0 observations with duplicate key values were deleted.
NOTE: There were 5426 observations read from the data set WORK.MIGRANT00B.
NOTE: The data set WORK.SMIGRANT00B has 5426 observations and 4 variables.
NOTE: PROCEDURE SORT used:
      real time           0.12 seconds
      cpu time            0.08 seconds
      
422        
423        * 3. Match SMIGRANT00B to the MINDIV00 Data File *
424        ---------------------------------------------------;
425        data mindiv00_nrpid notin_mindiv00 notin_migrant00b;
426          merge smigrant00b(in=a)
427                in8.mindiv00(in=b);
428          by MID00 MIGTYPE MCEP00;
429        
430          if a=1 and b=1 then output mindiv00_nrpid;
431          if a=1 and b=0 then output notin_mindiv00;
432          if a=0 and b=1 then output notin_migrant00b;
433        
434        run;

NOTE: There were 5426 observations read from the data set WORK.SMIGRANT00B.
NOTE: There were 5426 observations read from the data set IN8.MINDIV00.
NOTE: The data set WORK.MINDIV00_NRPID has 5426 observations and 537 variables.
NOTE: The data set WORK.NOTIN_MINDIV00 has 0 observations and 537 variables.
NOTE: The data set WORK.NOTIN_MIGRANT00B has 0 observations and 537 variables.
NOTE: DATA statement used:
      real time           6.39 seconds
      cpu time            6.29 seconds
      

435        
436        *** Check for Duplicates on NRPID in MINDIV00_NRPID (SHOULD HAVE 14!) ***;
437        
438        proc sort data=mindiv00_nrpid out=smindiv00_nrpid nodupkey;
439          by NRPID;
440        run;

NOTE: 14 observations with duplicate key values were deleted.
NOTE: There were 5426 observations read from the data set WORK.MINDIV00_NRPID.
NOTE: The data set WORK.SMINDIV00_NRPID has 5412 observations and 537 variables.
NOTE: PROCEDURE SORT used:
      real time           4.74 seconds
      cpu time            3.06 seconds