Add the Person Identifier (NRPID) to the 1994 Moved Household data

******************************************************************************
Attach NRPID to the 1994 Moved Household Individual-Level Data File
   1. Select ONLY 1984 Individuals in the PERSONID Data File
   2. Match SPERSON84 to the MOVED94 Data File

Input data: /nangrong/personid.X01
            /nangrong/1994/moved94.02
*****************************************************************************;

libname in1 xport '/nangrong/personid.X01';
libname in2 xport '/nangrong/1994/moved94.02';

*************************************************************************
*  Attach NRPID to the 1994 Moved Household Individual-Level Data File  *
*************************************************************************;

* 1. Select ONLY 1984 Individuals in the PERSONID Data File *
--------------------------------------------------------------;
data person84;
  set in1.personid(keep=VILL84 HOUSE84 CEP84 NRPID);

  if (HOUSE84 ne ' ');

run;

*** Sort PERSON84 by VILL84 HOUSE84 CEP84 ***;

proc sort data=person84 out=sperson84 nodupkey;
  by VILL84 HOUSE84 CEP84;
run;

* 2. Match SPERSON84 to the MOVED94 Data File *
------------------------------------------------;
data moved94_nrpid notin_moved94 notin_person84b;
  merge sperson84(in=a)
        in2.moved94(in=b);
  by VILL84 HOUSE84 CEP84;

  if a=1 and b=1 then output moved94_nrpid;
  if a=1 and b=0 then output notin_moved94;
  if a=0 and b=1 then output notin_person84b;

run;

*** Check for Duplicates on NRPID in MOVED94_NRPID ***;

proc sort data=moved94_nrpid out=smoved94_nrpid nodupkey;
  by NRPID;
run;

167        *************************************************************************
168        *  Attach NRPID to the 1994 Moved Household Individual-Level Data File  *
169        *************************************************************************;
170        
171        * 1. Select ONLY 1984 Individuals in the PERSONID Data File *
172        --------------------------------------------------------------;
173        data person84;
174          set in1.personid(keep=VILL84 HOUSE84 CEP84 NRPID);
175        
176          if (HOUSE84 ne ' ');
177        
178        run;

NOTE: There were 57416 observations read from the data set IN1.PERSONID.
NOTE: The data set WORK.PERSON84 has 34035 observations and 4 variables.
NOTE: DATA statement used:
      real time           0.78 seconds
      cpu time            0.76 seconds
      

179        
180        *** Sort PERSON84 by VILL84 HOUSE84 CEP84 ***;
181        
182        proc sort data=person84 out=sperson84 nodupkey;
183          by VILL84 HOUSE84 CEP84;
184        run;

NOTE: 0 observations with duplicate key values were deleted.
NOTE: There were 34035 observations read from the data set WORK.PERSON84.
NOTE: The data set WORK.SPERSON84 has 34035 observations and 4 variables.
NOTE: PROCEDURE SORT used:
      real time           0.40 seconds
      cpu time            0.37 seconds
      

185        
186        * 2. Match SPERSON84 to the MOVED94 Data File *
187        ------------------------------------------------;
188        data moved94_nrpid notin_moved94 notin_person84b;
189          merge sperson84(in=a)
190                in4.moved94(in=b);
191          by VILL84 HOUSE84 CEP84;
192        
193          if a=1 and b=1 then output moved94_nrpid;
194          if a=1 and b=0 then output notin_moved94;
195          if a=0 and b=1 then output notin_person84b;
196        
197        run;

NOTE: There were 34035 observations read from the data set WORK.SPERSON84.
NOTE: There were 3187 observations read from the data set IN4.MOVED94.
NOTE: The data set WORK.MOVED94_NRPID has 3187 observations and 15 variables.
NOTE: The data set WORK.NOTIN_MOVED94 has 30848 observations and 15 variables.
NOTE: The data set WORK.NOTIN_PERSON84B has 0 observations and 15 variables.
NOTE: DATA statement used:
      real time           1.29 seconds
      cpu time            1.21 seconds
      

198        
199        *** Check for Duplicates on NRPID in MOVED94_NRPID ***;
200        
201        proc sort data=moved94_nrpid out=smoved94_nrpid nodupkey;
202          by NRPID;
203        run;

NOTE: 0 observations with duplicate key values were deleted.
NOTE: There were 3187 observations read from the data set WORK.MOVED94_NRPID.
NOTE: The data set WORK.SMOVED94_NRPID has 3187 observations and 15 variables.
NOTE: PROCEDURE SORT used:
      real time           0.12 seconds
      cpu time            0.07 seconds