Add the Person Identifier (NRPID) to the 1994 data

******************************************************************************
Attach NRPID to the 1994 Individual-Level Data File
   1. Select ONLY 1994 Individuals in the PERSONID Data File
   2. Restructure PERSON94 into "Child" File, 
      as 2516 Code 2 Individuals are in the data TWICE
   3. Match SPERSON94B to the INDIV94 Data File.

Input data: /nangrong/personid.X01
            /nangrong/1994/indiv94.03
*****************************************************************************;

libname in1 xport '/nangrong/personid.X01';
libname in2 xport '/nangrong/1994/indiv94.03';

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

* 1. Select ONLY 1994 Individuals in the PERSONID Data File *
--------------------------------------------------------------;
data person94;
  set in1.personid(keep=HHID94 CEP94 OHHID94 OCEP94 NRPID);

  if (HHID94 ne .);

*** Rename Identifiers ***;

rename
HHID94=DHHID94
CEP94=DCEP94
;

run;

* 2. Restructure PERSON94 into "Child" File, 
     as 2516 Code 2 Individuals are in the data TWICE *
--------------------------------------------------------;
data person94b;
  set person94;
  length CEP94 $ 3;

  keep HHID94 CEP94 NRPID;

  array i1 {2} DHHID94 OHHID94;
  array i2 {2} DCEP94 OCEP94;

  do i=1 to 2;
   HHID94=i1{i};
   CEP94=i2{i};
   if HHID94 ne . then output;
  end; 

run;

*** Sort PERSON94B by HHID94 CEP94 ***;

proc sort data=person94b out=sperson94b nodupkey;
  by HHID94 CEP94;
run;

* 3. Match SPERSON94B to the INDIV94 Data File *
-------------------------------------------------;
data indiv94_nrpid notin_indiv94 notin_person94a;
  merge sperson94b(in=a)
        in3.indiv94(in=b);
  by HHID94 CEP94;

  if a=1 and b=1 then output indiv94_nrpid;
  if a=1 and b=0 then output notin_indiv94;
  if a=0 and b=1 then output notin_person94a; 

run;

*** Check for Duplicates on NRPID in INDIV94_NRPID (SHOULD HAVE 2516!) ***;

proc sort data=indiv94_nrpid out=sindiv94_nrpid nodupkey;
  by NRPID;
run;

102        *********************************************************
103        *  Attach NRPID to the 1994 Individual-Level Data File  *
104        *********************************************************;
105        
106        * 1. Select ONLY 1994 Individuals in the PERSONID Data File *
107        --------------------------------------------------------------;
108        data person94;
109          set in1.personid(keep=HHID94 CEP94 OHHID94 OCEP94 NRPID);
110        
111          if (HHID94 ne .);
112        
113        *** Rename Identifiers ***;
114        
115        rename
116        HHID94=DHHID94
117        CEP94=DCEP94
118        ;
119       
120        run;

NOTE: There were 57416 observations read from the data set IN1.PERSONID.
NOTE: The data set WORK.PERSON94 has 42249 observations and 5 variables.
NOTE: DATA statement used:
      real time           0.95 seconds
      cpu time            0.92 seconds
      

121        
122        * 2. Restructure PERSON94 into "Child" File,
                as 2516 Code 2 Individuals are in data TWICE *
123        ----------------------------------------------------;
124        data person94b;
125          set person94;
126          length CEP94 $ 3;
127        
128          keep HHID94 CEP94 NRPID;
129        
130          array i1 {2} DHHID94 OHHID94;
131          array i2 {2} DCEP94 OCEP94;
132        
133          do i=1 to 2;
134           HHID94=i1{i};
135           CEP94=i2{i};
136           if HHID94 ne . then output;
137          end;
138        
139        run;

NOTE: There were 42249 observations read from the data set WORK.PERSON94.
NOTE: The data set WORK.PERSON94B has 44765 observations and 3 variables.
NOTE: DATA statement used:
      real time           0.45 seconds
      cpu time            0.43 seconds

140        
141        *** Sort PERSON94B by HHID94 CEP94 ***;
142        
143        proc sort data=person94b out=sperson94b nodupkey;
144          by HHID94 CEP94;
145        run;

NOTE: 0 observations with duplicate key values were deleted.
NOTE: There were 44765 observations read from the data set WORK.PERSON94B.
NOTE: The data set WORK.SPERSON94B has 44765 observations and 3 variables.
NOTE: PROCEDURE SORT used:
      real time           0.60 seconds
      cpu time            0.56 seconds
      

146        
147        * 3. Match SPERSON94B to the INDIV94 Data File *
148        -------------------------------------------------;
149        data indiv94_nrpid notin_indiv94 notin_person94a;
150          merge sperson94b(in=a)
151                in3.indiv94(in=b);
152          by HHID94 CEP94;
153        
154          if a=1 and b=1 then output indiv94_nrpid;
155          if a=1 and b=0 then output notin_indiv94;
156          if a=0 and b=1 then output notin_person94a;
157        
158        run;

NOTE: There were 44765 observations read from the data set WORK.SPERSON94B.
NOTE: There were 44765 observations read from the data set IN3.INDIV94.
NOTE: The data set WORK.INDIV94_NRPID has 44765 observations and 70 variables.
NOTE: The data set WORK.NOTIN_INDIV94 has 0 observations and 70 variables.
NOTE: The data set WORK.NOTIN_PERSON94A has 0 observations and 70 variables.
NOTE: DATA statement used:
      real time           10.19 seconds
      cpu time            9.81 seconds
      

159        
160        *** Check for Duplicates on NRPID in INDIV94_NRPID (SHOULD HAVE 2516!) ***;
161        
162        proc sort data=indiv94_nrpid out=sindiv94_nrpid nodupkey;
163          by NRPID;
164        run;

NOTE: 2516 observations with duplicate key values were deleted.
NOTE: There were 44765 observations read from the data set WORK.INDIV94_NRPID.
NOTE: The data set WORK.SINDIV94_NRPID has 42249 observations and 70 variables.
NOTE: PROCEDURE SORT used:
      real time           3.21 seconds
      cpu time            2.22 seconds