/* creates a comprehensive SAS data set in a rectangular ("flat") format: one
 * record for each person in the sample, containing every variable from both
 * record types (even the allocation flags), plus a record for each vacant
 * housing unit, with the Person-record variables set to "missing". */
libname pums 'c:\sas';
data pums.pumsbxde;
infile 'd:\pumsbxde.txt' lrecl=231;
input @1 RecType $ 1. @;
if RecType = 'H' then 
        do; *(Household record);
        input    @2 SerialNo $ 7.
                 @9 Sample   $ 1.
                @10 Division $ 1.
                @11 State    $ 2.
                @13 PUMA     $ 5.
                @18 AreaType $ 2.
                @20 MSAPMSA  $ 4.
                @24 PSA      $ 3.
                @27 SubSampl $ 2.
                @29 HousWgt    4.
                @33 Persons    2.
                @35 GQType   $ 1.
                @39 Units1   $ 2.
                @41 HUSFlag  $ 1.
                @42 PDSFlag  $ 1.
                @43 Rooms    $ 1.
                @44 Tenure   $ 1.
                @45 Acreage  $ 1.
                @46 CommUse  $ 1.
                @47 Value    $ 2.
                @49 Rent1    $ 2.
                @51 Meals    $ 1.
                @52 Vacancy1 $ 1.
                @53 Vacancy2 $ 1.
                @54 Vacancy3 $ 1.
                @55 Vacancy4 $ 1.
                @56 YrMoved  $ 1.
                @57 Bedrooms $ 1.
                @58 Plumbing $ 1.
                @59 Kitchen  $ 1.
                @60 Telephon $ 1.
                @61 Vehicles $ 1.
                @62 Fuel     $ 1.
                @63 Water    $ 1.
                @64 Sewage   $ 1.
                @65 YrBuilt  $ 1.
                @66 Condo    $ 1.
                @67 OneAcre  $ 1.
                @68 AgSales  $ 1.
                @69 ElecCost   4.
                @73 GasCost    4.
                @77 WatrCost   4.
                @81 FuelCost   4.
                @85 PropTax  $ 2.
                @90 PropIns    4.
                @94 Mortgage $ 1.
                @95 Mortgag3   5.
                @100 TaxIncl  $ 1.
                @101 InsIncl  $ 1.
                @102 Mortgag2 $ 1.
                @103 MortAmt2   5.
                @108 CondoFee   4.
                @112 Moblhome   4.
                @116 RFarm    $ 1.
                @117 RGRent     4.
                @121 RGRAPI   $ 2.
                @124 ROwnrCst   4.
                @129 RNSMOCPI   3.
                @132 RRentUnt $ 1.
                @133 RValUnt  $ 1.
                @134 RFamInc    7.
                @141 RHhInc     7.
                @148 RWrkr89  $ 1.
                @149 RHhLang  $ 1.
                @150 RLingIso $ 1.
                @151 RHhFamTp $ 2.
                @153 RNatAdpt   2.
                @155 RStpChld   2.
                @157 RFamPers   2.
                @159 RRelChld   2.
                @161 RNonRel  $ 1.
                @162 R18Undr  $ 1.
                @163 R60Over  $ 1.
                @164 R65Over  $ 1.
                @165 RSubFam  $ 1.
                @166 AUnits1  $ 1.
                @167 ARooms   $ 1.
                @168 ATenure  $ 1.
                @169 AAcres1  $ 1.
                @170 ACommuse $ 1.
                @171 AValue   $ 1.
                @172 ARent1   $ 1.
                @173 AMeals   $ 1.
                @174 AVacncy2 $ 1.
                @175 AVacncy3 $ 1.
                @176 AVacncy4 $ 1.
                @177 AYrMoved $ 1.
                @178 ABedRoom $ 1.
                @179 APlumbng $ 1.
                @180 AKitchen $ 1.
                @181 APhone   $ 1.
                @182 AVehicle $ 1.
                @183 AFuel    $ 1.
                @184 AWater   $ 1.
                @185 ASewer   $ 1.
                @186 AYrBuilt $ 1.
                @187 ACondo   $ 1.
                @188 AOneAcre $ 1.
                @189 AAgSales $ 1.
                @190 AElecCst $ 1.
                @191 AGasCst  $ 1.
                @192 AWatrCst $ 1.
                @193 AFuelCst $ 1.
                @194 ATaxAmt  $ 1.
                @195 AInsAmt  $ 1.
                @196 AMortg   $ 1.
                @197 AMortg3  $ 1.
                @198 ATaxIncl $ 1.
                @199 AInsIncl $ 1.
                @200 AMortg2  $ 1.
                @201 AMrtAmt2 $ 1.
                @202 ACndoFee $ 1.
                @203 AMoblHme $ 1.;
                if Persons=0 then output; *Vacant: P-rec vars will be missing;
        end;
else
        do; *(Person record);
        input    @2 SerialNo $ 7.
                 @9 Relat1   $ 2.
                @11 Sex      $ 1.
                @12 Race     $ 3.
                @15 Age        2.
                @17 Marital  $ 1.
                @18 PWgt1      4.
                @26 REmplPar $ 3.
                @29 RPOB     $ 2.
                @31 RSpouse  $ 1.
                @32 ROwnChld $ 1.
                @33 RAgeChld $ 1.
                @34 RRelChl2 $ 1.
                @35 Relat2   $ 1.
                @36 SubFam2  $ 1.
                @37 SubFam1  $ 1.
                @38 Hispanic $ 3.
                @41 Poverty  $ 3.
                @44 POB      $ 3.
                @47 Citizen  $ 1.
                @48 Immigr   $ 2.
                @50 School   $ 1.
                @51 YearSch  $ 2.
                @53 Ancstry1 $ 3.
                @56 Ancstry2 $ 3.
                @59 Mobility $ 1.
                @60 MigrStat $ 2.
                @62 MigPUMA  $ 5.
                @67 Lang1    $ 1.
                @68 Lang2    $ 3.
                @71 English  $ 1.
                @72 Military $ 1.
                @73 RVetServ $ 2.
                @75 Sept80   $ 1.
                @76 May75880 $ 1.
                @77 Vietnam  $ 1.
                @78 Feb55    $ 1.
                @79 Korean   $ 1.
                @80 WWII     $ 1.
                @82 OthrServ $ 1.
                @83 YrsServ  $ 2.
                @85 Disabl1  $ 1.
                @86 Disabl2  $ 1.
                @87 MobilLim $ 1.
                @88 PersCare $ 1.
                @89 Fertil   $ 1.
                @91 RLabor   $ 1.
                @92 WorkLwk  $ 1.
                @93 Hours    $ 2.
                @95 POWState $ 2.
                @97 POWPUMA  $ 5.
                @102 Means    $ 2.
                @104 Riders   $ 1.
                @105 Depart   $ 4.
                @109 TravTime $ 2.
                @111 TmpAbsnt $ 1.
                @112 Looking  $ 1.
                @113 Avail    $ 1.
                @114 YearWrk  $ 1.
                @115 Industry $ 3.
                @118 Occup    $ 3.
                @121 Class    $ 1.
                @122 Work89   $ 1.
                @123 Week89   $ 2.
                @125 Hour89   $ 2.
                @127 REarning   6.
                @133 RPIncome   6.
                @139 Income1    6.
                @145 Income2    6.
                @151 Income3    6.
                @157 Income4    6.
                @163 Income5    5.
                @168 Income6    5.
                @173 Income7    5.
                @178 Income8    5.
                @183 AAugment $ 1.
                @184 ARelat1  $ 1.
                @185 ASex     $ 1.
                @186 ARace    $ 1.
                @187 AAge     $ 1.
                @188 AMarital $ 1.
                @189 AHispan  $ 1.
                @190 ABirthPl $ 1.
                @191 ACitizen $ 1.
                @192 AImmigr  $ 1.
                @193 ASchool  $ 1.
                @194 AYearSch $ 1.
                @195 AAncstr1 $ 1.
                @196 AAncstr2 $ 1.
                @197 AMoblty  $ 1.
                @198 AMigStat $ 1.
                @199 ALang1   $ 1.
                @200 ALang2   $ 1.
                @201 AEnglish $ 1.
                @202 AVetS1   $ 1.
                @203 AServPer $ 1.
                @204 AYrsServ $ 1.
                @205 ADisAbl1 $ 1.
                @206 ADisAbl2 $ 1.
                @207 AMoblLim $ 1.
                @208 APerCare $ 1.
                @209 AFERTIL  $ 1.
                @210 ALabor   $ 1.
                @211 AHours   $ 1.
                @212 APOWSt   $ 1.
                @213 AMeans   $ 1.
                @214 ARiders  $ 1.
                @215 ADepart  $ 1.
                @216 ATranTme $ 1.
                @217 ALstWrk  $ 1.
                @218 AIndustr $ 1.
                @219 AOccup   $ 1.
                @220 AClass   $ 1.
                @221 AWork89  $ 1.
                @222 AWks89   $ 1.
                @223 AHour89  $ 1.
                @224 AIncome1 $ 1.
                @225 AIncome2 $ 1.
                @226 AIncome3 $ 1.
                @227 AIncome4 $ 1.
                @228 AIncome5 $ 1.
                @229 AIncome6 $ 1.
                @230 AIncome7 $ 1.
                @231 AIncome8 $ 1.;
                output;
        end;
/* Need Retain statement for H-record variables only: don't want them set to
 * "missing" each time you read a P-record, but do want P-rec vars to be
 * "missing" in records for vacant housing units */
retain SerialNo--AMoblHme;
* You may want to add a Keep or Drop statement to eliminate unneeded variables
  (or just delete them from the above lists) and a Length statement (default=3
  except for income, rent, cost vars, etc.) to make the saved data set smaller;
run;