Add the Person Identifier (NRPID) to the 1984 data

******************************************************************************
Attach NRPID to the 1984 Individual-Level Data File (indiv84)
   1. Select ONLY 1984 Individuals in the PERSONID Data File
   2. Match SPERSON84 to the INDIV84 Data File

Input data: /nangrong/personid.X01
            /nangrong/1984/indiv84.02
*****************************************************************************;

libname in1 xport '/nangrong/personid.X01';
libname in2 xport '/nangrong/1984/indiv84.02';

*******************************************************************
*  Attach NRPID to the 1984 Individual-Level Data File (indiv84)  *
*******************************************************************;

* 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 INDIV84 Data File *
------------------------------------------------;
data indiv84_nrpid notin_indiv84 notin_person84a;
  merge sperson84(in=a)
        in2.indiv84(in=b);
  by VILL84 HOUSE84 CEP84;

  if a=1 and b=1 then output indiv84_nrpid;
  if a=1 and b=0 then output notin_indiv84;
  if a=0 and b=1 then output notin_person84a;

run;

*** Check for Duplicates on NRPID in INDIV84_NRPID ***;

proc sort data=indiv84_nrpid out=sindiv84_nrpid nodupkey;
  by NRPID;
run;

62         
63         *******************************************************************
64         *  Attach NRPID to the 1984 Individual-Level Data File (indiv84)  *
65         *******************************************************************;
66         
67         * 1. Select ONLY 1984 Individuals in the PERSONID Data File *
68         --------------------------------------------------------------;
69         data person84;
70           set in1.personid(keep=VILL84 HOUSE84 CEP84 NRPID);
71         
72           if (HOUSE84 ne ' ');
73         
74         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           0.83 seconds
      cpu time            0.80 seconds
      

75         
76         *** Sort PERSON84 by VILL84 HOUSE84 CEP84 ***;
77         
78         proc sort data=person84 out=sperson84 nodupkey;
79           by VILL84 HOUSE84 CEP84;
80         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            0.38 seconds
      

81         
82         * 2. Match SPERSON84 to the INDIV84 Data File *
83         ------------------------------------------------;
84         data indiv84_nrpid notin_indiv84 notin_person84a;
85           merge sperson84(in=a)
86                 in2.indiv84(in=b);
87           by VILL84 HOUSE84 CEP84;
88         
89           if a=1 and b=1 then output indiv84_nrpid;
90           if a=1 and b=0 then output notin_indiv84;
91           if a=0 and b=1 then output notin_person84a;
92         
93         run;

NOTE: There were 34035 observations read from the data set WORK.SPERSON84.
NOTE: There were 34035 observations read from the data set IN2.INDIV84.
NOTE: The data set WORK.INDIV84_NRPID has 34035 observations and 26 variables.
NOTE: The data set WORK.NOTIN_INDIV84 has 0 observations and 26 variables.
NOTE: The data set WORK.NOTIN_PERSON84A has 0 observations and 26 variables.
NOTE: DATA statement used:
      real time           3.18 seconds
      cpu time            3.07 seconds
      

94         
95         *** Check for Duplicates on NRPID in INDIV84_NRPID ***;
96         
97         proc sort data=indiv84_nrpid out=sindiv84_nrpid nodupkey;
98           by NRPID;
99         run;

NOTE: 0 observations with duplicate key values were deleted.
NOTE: There were 34035 observations read from the data set WORK.INDIV84_NRPID.
NOTE: The data set WORK.SINDIV84_NRPID has 34035 observations and 26 variables.
NOTE: PROCEDURE SORT used:
      real time           1.10 seconds
      cpu time            0.79 seconds