Linking Example: Use the NHIS-MEPS Link File to link 2001 MEPS data with 1999 and 2000

1 The SAS System 13:08 Sunday, November 21, 2004

NOTE: SAS (r) Proprietary Software Release 8.2 (TS2M0)

Licensed to AGENCY FOR HEALTHCARE RESEARCH & QUALITY, Site 0040776001.

NOTE: This session is executing on the WIN_PRO platform.

1 options ls=120 ps=79 nodate;

2 ods noproctitle;

3 /************************************************************************************\

4 Program: c:\meps\prog\Example_L2.sas

6 Description: This example shows how to:

7 (1) Create SAS files from ASCII files

8 (2) Link 2001 MEPS to 1999 and 2000 NHIS

9 (3) Compare persons' status in NHIS with their status in MEPS

11 Input Files: c:\meps\data\nhisper99.dat (1999 NHIS Persons, renamed from PERSONSX)

12 c:\meps\data\nhisper00.dat (2000 NHIS Persons, renamed from PERSONSX)

13 c:\meps\data\nhmep01x.dat (NHIS-MEPS Link File - read in from diskette)

14 c:\meps\data\h60.sas7bdat (2001 MEPS Persons)

15 \************************************************************************************/

17 libname hc 'c:\meps\data';

NOTE: Libref HC was successfully assigned as follows:

Engine: V8

Physical Name: c:\meps\data

19 filename n99 'c:\meps\data\nhisper99.dat';

20 filename n00 'c:\meps\data\nhisper00.dat';

21 filename lnk 'c:\meps\data\nhmep01x.dat';

23 title 'AHRQ MEPS DATA USERS WORKSHOP (LINKING) -- NOV/DEC 2004';

24 title2 'NHIS-MEPS Link';

26 proc format;

27 value anylim

28 -9='-9 Not Ascer'

29 -1='-1 Inapp'

30 1='1 Yes'

31 2='2 No';

NOTE: Format ANYLIM has been output.

32 value sex 1='1 Male' 2='2 Female';

NOTE: Format SEX has been output.

33 value hstat

34 -9='-9 Not Ascer'

35 -8='-8 DK'

36 -7='-7 Refused'

37 -1='-1 Inapp'

38 1='1 Excellent'

39 2='2 Very Good'

40 3='3 Good'

41 4='4 Fair'

42 5='5 Poor'

43 7='7 Refused'

44 8='8 Not Ascer'

45 9='9 DK';

NOTE: Format HSTAT has been output.

46 value nhislim

47 1='1 Limited'

48 2='2 Not Limited'

49 3='3 Unknown'

50 7='7 Refused'

51 8='8 Not Ascer'

52 9='9 DK';

NOTE: Format NHISLIM has been output.

53 value nhischron

NOTE: The format name 'NHISCHRON' exceeds 8 characters. Only the first 8 characters will be used.

54 0='0 Not Limited'

55 1='1 Lim, 1+ Chron Cond'

56 2='2 Lim, Not Chron'

57 3='3 Lim, Chron Unk'

58 7='7 Refused'

59 8='8 Not Ascer'

60 9='9 DK';

NOTE: Format NHISCHRO has been output.

61 run;

2 The SAS System

63 title3 '2001 MEPS';

64 data meps01; set hc.h60(keep=dupersid anylim01 rthlth31 rthlth42 rthlth53

65 perwt01f varstr01 varpsu01); by dupersid; /* file is already sorted */

66 /* construct annual health status from last nonmissing round variable */

67 if rthlth53 > 0 then MEPSHSTAT=rthlth53;

68 else if rthlth42 > 0 then MEPSHSTAT=rthlth42;

69 else if rthlth31 > 0 then MEPSHSTAT=rthlth31;

70 label mepshstat='MEPS Health Status';

71 run;

NOTE: There were 33556 observations read from the data set HC.H60.

NOTE: The data set WORK.MEPS01 has 33556 observations and 9 variables.

72 proc contents position; run;

NOTE: The PROCEDURE CONTENTS printed page 1.

73 proc print data=_last_(obs=60); run;

NOTE: There were 60 observations read from the data set WORK.MEPS01.

NOTE: The PROCEDURE PRINT printed page 2.

74 title4 'Verify New Variable';

75 proc freq; tables

76 mepshstat

77 mepshstat*rthlth53*rthlth42*rthlth31/list missing;

78 format mepshstat rthlth53 rthlth42 rthlth31 hstat.;

79 run;

NOTE: There were 33556 observations read from the data set WORK.MEPS01.

NOTE: The PROCEDURE FREQ printed pages 3-6.

81 title3 'Link File';

82 data link; infile lnk; input

83 DUPERSID $1-8

84 HHX $9-14

85 PX $15-16

86 LINKFLAG 17

87 SRVY_YR 19-22;

88 run;

NOTE: The infile LNK is:

File Name=c:\meps\data\nhmep01x.dat,

RECFM=V,LRECL=256

NOTE: 33556 records were read from the infile LNK.

The minimum record length was 22.

The maximum record length was 22.

NOTE: The data set WORK.LINK has 33556 observations and 5 variables.

89 proc sort; by dupersid; run;

NOTE: There were 33556 observations read from the data set WORK.LINK.

NOTE: The data set WORK.LINK has 33556 observations and 5 variables.

90 proc contents position; run;

NOTE: The PROCEDURE CONTENTS printed page 7.

91 proc print data=_last_(obs=60); run;

NOTE: There were 60 observations read from the data set WORK.LINK.

NOTE: The PROCEDURE PRINT printed page 8.

92 proc freq; tables linkflag srvy_yr; run;

NOTE: There were 33556 observations read from the data set WORK.LINK.

NOTE: The PROCEDURE FREQ printed page 9.

94 title3 '1999 NHIS';

95 data nhis99; infile n99 missover lrecl=829; input

96 SRVY_YR 3-6

3 The SAS System

97 HHX $7-12

98 PX $15-16

99 SEX 18

100 AGE 19-20

101 NHISLIM 120

102 NHISCHRON 563

103 NHISHSTAT 564;

104 label

105 nhislim ='NHIS Any Limitation'

106 nhischron="NHIS Lim'n/Chronic Status"

107 nhishstat='NHIS Health Status';

108 run;

NOTE: The infile N99 is:

File Name=c:\meps\data\nhisper99.dat,

RECFM=V,LRECL=829

NOTE: 97059 records were read from the infile N99.

The minimum record length was 829.

The maximum record length was 829.

NOTE: The data set WORK.NHIS99 has 97059 observations and 8 variables.

109 proc sort; by hhx px srvy_yr; run;

NOTE: There were 97059 observations read from the data set WORK.NHIS99.

NOTE: The data set WORK.NHIS99 has 97059 observations and 8 variables.

110 proc contents position; run;

NOTE: The PROCEDURE CONTENTS printed page 10.

111 proc print data=_last_(obs=60); run;

NOTE: There were 60 observations read from the data set WORK.NHIS99.

NOTE: The PROCEDURE PRINT printed page 11.

112

113 title3 '2000 NHIS';

114 data nhis00; infile n00 missover lrecl=789; input

115 SRVY_YR 3-6

116 HHX $7-12

117 PX $15-16

118 SEX 18

119 AGE 19-20

120 NHISLIM 123

121 NHISCHRON 566

122 NHISHSTAT 567;

123 label

124 nhislim ='NHIS Any Limitation'

125 nhischron="NHIS Lim'n/Chronic Status"

126 nhishstat='NHIS Health Status';

127 run;

NOTE: The infile N00 is:

File Name=c:\meps\data\nhisper00.dat,

RECFM=V,LRECL=789

NOTE: 100618 records were read from the infile N00.

The minimum record length was 789.

The maximum record length was 789.

NOTE: The data set WORK.NHIS00 has 100618 observations and 8 variables.

128 proc sort; by hhx px srvy_yr; run;

NOTE: There were 100618 observations read from the data set WORK.NHIS00.

NOTE: The data set WORK.NHIS00 has 100618 observations and 8 variables.

129 proc contents position; run;

NOTE: The PROCEDURE CONTENTS printed page 12.

130 proc print data=_last_(obs=60); run;

NOTE: There were 60 observations read from the data set WORK.NHIS00.

NOTE: The PROCEDURE PRINT printed page 13.

131

4 The SAS System

132 title3 'Combine Link File & MEPS --> MEPSLINK';

133 data mepslink; merge

134 meps01(in=a drop=rthlth31 rthlth42 rthlth53)

135 link(in=b drop=linkflag); by dupersid; if a & b;

136 run;

NOTE: There were 33556 observations read from the data set WORK.MEPS01.

NOTE: There were 33556 observations read from the data set WORK.LINK.

NOTE: The data set WORK.MEPSLINK has 33556 observations and 9 variables.

137 proc sort; by hhx px srvy_yr; run;

NOTE: There were 33556 observations read from the data set WORK.MEPSLINK.

NOTE: The data set WORK.MEPSLINK has 33556 observations and 9 variables.

138 proc contents position; run;

NOTE: The PROCEDURE CONTENTS printed page 14.

139 proc print data=_last_(obs=60); run;

NOTE: There were 60 observations read from the data set WORK.MEPSLINK.

NOTE: The PROCEDURE PRINT printed page 15.

140

141 title3 'Combine 1999 & 2000 NHIS Files --> NHIS';

142 data nhis; merge

143 nhis99

144 nhis00; by hhx px srvy_yr;

145 run;

NOTE: There were 97059 observations read from the data set WORK.NHIS99.

NOTE: There were 100618 observations read from the data set WORK.NHIS00.

NOTE: The data set WORK.NHIS has 197677 observations and 8 variables.

146 proc contents position; run;

NOTE: The PROCEDURE CONTENTS printed page 16.

147 proc print data=_last_(obs=60); run;

NOTE: There were 60 observations read from the data set WORK.NHIS.

NOTE: The PROCEDURE PRINT printed page 17.

148

149 title3 'Combine MEPSLINK & NHIS --> TOTAL01';

150 data total01; merge

151 mepslink(in=a)

152 nhis(in=b); by hhx px srvy_yr; if a & b;

153 run;

NOTE: There were 33556 observations read from the data set WORK.MEPSLINK.

NOTE: There were 197677 observations read from the data set WORK.NHIS.

NOTE: The data set WORK.TOTAL01 has 29795 observations and 14 variables.

154 proc contents position; run;

NOTE: The PROCEDURE CONTENTS printed page 18.

155 proc print data=_last_(obs=60); run;

NOTE: There were 60 observations read from the data set WORK.TOTAL01.

NOTE: The PROCEDURE PRINT printed page 19.

156

157 title3 'Unweighted';

158 proc freq; tables

159 anylim01 mepshstat sex nhislim nhischron nhishstat/missing;

160 format anylim01 anylim. mepshstat nhishstat hstat. sex sex. nhislim nhislim.

161 nhischron nhischron.;

162 run;

NOTE: There were 29795 observations read from the data set WORK.TOTAL01.

NOTE: The PROCEDURE FREQ printed page 20.

163 proc means n nmiss min max maxdec=0; var age; run;

5 The SAS System

NOTE: There were 29795 observations read from the data set WORK.TOTAL01.

NOTE: The PROCEDURE MEANS printed page 21.

164

165 title3 'Weighted';

166 title4 'Compare Limitation Status and Health Status Over Time';

167 proc freq; tables

168 nhislim*anylim01

169 nhishstat*mepshstat/list missing;

170 format nhislim nhislim. anylim01 anylim. nhishstat mepshstat hstat.;

171 weight perwt01f;

172 run;

NOTE: There were 29795 observations read from the data set WORK.TOTAL01.

NOTE: The PROCEDURE FREQ printed page 22.

NOTE: SAS Institute Inc., SAS Campus Drive, Cary, NC USA 27513-2414

Obs DUPERSID RTHLTH31 RTHLTH42 RTHLTH53 ANYLIM01 PERWT01F VARSTR01 VARPSU01 MEPSHSTAT

-----------------------------------------------------------------------------------------------------------------