* Wealth index calculation. Trevor Croft, 06/30/2021. India NFHS 2019-20.
cd 'C:\Users\21180\OneDrive - ICF\Projects\Analysis\Wealth Index Construction\IA2019-20 (Jun 2021)\Wealth'.
include file='wealth_assets.sps'.
missing values QH65 (999.9).
execute.
set tvars=both.

* Macro definitions to perform some recoding automatically.
* Note: Do not use an asterisk in front of a macro name to try to comment it out - it will run any way because of the way the macros are expanded.
* Delete the line instead or change the spelling of the macro in the comment.
* Do not use the names of macros in comments - they will also be expanded too, and likely will fail.

*{Create binary variables based on condition and give label }.
define dichotomize( !positional !enclose('(',')') / !positional !tokens(1) / !positional !tokens(1) )
compute !2=0.
if (!1) !2=1.
variable labels !2 !3.
value labels !2 0 'No' 1 'Yes'.
formats !2 (f1.0).
!enddefine.

*(Separate shared toilets from non-shared toilets).
define shared_fac( !positional !tokens(1) / !positional !tokens(1) / !positional !tokens(1) ).
compute !2 = 0.
do if (QH42=1).
+ if (!1=1) !2 = 1.
+ compute !1 = 0.
end if.
variable labels !2 !3.
value labels !2 0 'No' 1 'Yes'.
formats !2 (f1.0).
!enddefine.

*{Reset missing values to 'does not have', change 2 code to 0}.
define no2zero( !positional !tokens(1) )
if (missing(!1) | !1<>1) !1=0.
value labels !1 0 'No' 1 'Yes'.
!enddefine.

*{Construct Variables}.

* Source of drinking water.
dichotomize (QH34=11) QH34_11 "Source of drinking water: Piped - into dwelling".
dichotomize (QH34=12) QH34_12 "Source of drinking water: Piped - into yard / plot".
dichotomize (QH34=13) QH34_13 "Source of drinking water: Piped - to neighbour".
dichotomize (QH34=14) QH34_14 "Source of drinking water: Piped - public tap / standpipe".
dichotomize (QH34=21) QH34_21 "Source of drinking water: Tube well / borehole".
dichotomize (QH34=31) QH34_31 "Source of drinking water: Dug well - protected".
dichotomize (QH34=32) QH34_32 "Source of drinking water: Dug well - unprotected".
dichotomize (QH34=41) QH34_41 "Source of drinking water: Spring water - protected".
dichotomize (QH34=42) QH34_42 "Source of drinking water: Spring water - unprotected".
dichotomize (QH34=51) QH34_51 "Source of drinking water: Rainwater".
dichotomize (QH34=61) QH34_61 "Source of drinking water: Tanker truck".
dichotomize (QH34=71) QH34_71 "Source of drinking water: Cart with small tank".
dichotomize (QH34=81) QH34_81 "Source of drinking water: Surface water (river / dam / lake / pond / stream / canal / irrigation channel)".
dichotomize (QH34=91) QH34_91 "Source of drinking water: Bottled water".
dichotomize (QH34=92) QH34_92 "Source of drinking water: Community RO Plant".
dichotomize (QH34=96) QH34_96 "Source of drinking water: Other".


* Type of toilet facility.
dichotomize (QH40=11) QH40_11 "Type of toilet facility: Flush - to piped sewer system".
dichotomize (QH40=12) QH40_12 "Type of toilet facility: Flush - to septic tank".
dichotomize (QH40=13) QH40_13 "Type of toilet facility: Flush - to pit latrine".
dichotomize (QH40=14) QH40_14 "Type of toilet facility: Flush - to somewhere else".
dichotomize (QH40=15) QH40_15 "Type of toilet facility: Flush - don't know where".
dichotomize (QH40=21) QH40_21 "Type of toilet facility: Ventilated Improved Single Pit (VIP) / biogas latrine".
dichotomize (QH40=22) QH40_22 "Type of toilet facility: Single pit latrine - with slab".
dichotomize (QH40=23) QH40_23 "Type of toilet facility: Single pit latrine - without slab / open pit".
dichotomize (QH40=31) QH40_31 "Type of toilet facility: Twin pit / composting toilet".
dichotomize (QH40=41) QH40_41 "Type of toilet facility: Dry toilet".
dichotomize (QH40=51) QH40_51 "Type of toilet facility: No facility / uses open space / or field".
dichotomize (QH40=96) QH40_96 "Type of toilet facility: Other".

shared_fac QH40_11 QH40_11_sh "Type of toilet facility: Flush - to piped sewer system - shared".
shared_fac QH40_12 QH40_12_sh "Type of toilet facility: Flush - to septic tank - shared".
shared_fac QH40_13 QH40_13_sh "Type of toilet facility: Flush - to pit latrine - shared".
shared_fac QH40_14 QH40_14_sh "Type of toilet facility: Flush - to somewhere else - shared".
shared_fac QH40_15 QH40_15_sh "Type of toilet facility: Flush - don't know where - shared".
shared_fac QH40_21 QH40_21_sh "Type of toilet facility: Ventilated Improved Single Pit (VIP) / biogas latrine - shared".
shared_fac QH40_22 QH40_22_sh "Type of toilet facility: Single pit latrine - with slab - shared".
shared_fac QH40_23 QH40_23_sh "Type of toilet facility: Single pit latrine - without slab / open pit - shared".
shared_fac QH40_31 QH40_31_sh "Type of toilet facility: Twin pit / composting toilet - shared".
shared_fac QH40_41 QH40_41_sh "Type of toilet facility: Dry toilet - shared".
shared_fac QH40_96 QH40_96_sh "Type of toilet facility: Other - shared".

* What type of drainage facility does this household have?.
dichotomize (QH46=1) QH46_1 "Type of drainage facility: Closed drainage".
dichotomize (QH46=2) QH46_2 "Type of drainage facility: Open drainage".
dichotomize (QH46=3) QH46_3 "Type of drainage facility: Drain to soak pit".
dichotomize (QH46=4) QH46_4 "Type of drainage facility: No drainage".

* Electricity.
no2zero QH50A.
* Mattress.
no2zero QH50B.
* Pressure cooker.
no2zero QH50C.
* Chair.
no2zero QH50D.
* Cot or bed.
no2zero QH50E.
* Table.
no2zero QH50F.
* Electric fan.
no2zero QH50G.
* Radio or transistor.
no2zero QH50H.
* Black and white television.
no2zero QH50I.
* Colour television.
no2zero QH50J.
* Sewing machine.
no2zero QH50K.
* Mobile telephone.
no2zero QH50L.
* Telephone (non-mobile).
no2zero QH50M.
* Internet.
no2zero QH50N.
* Computer.
no2zero QH50O.
* Refrigerator.
no2zero QH50P.
* Air conditioner/cooler.
no2zero QH50Q.
* Washing machine.
no2zero QH50R.
* Watch or clock.
no2zero QH50S.
* Bicycle.
no2zero QH50T.
* Motorcycle or Scooter.
no2zero QH50U.
* Animal-drawn cart.
no2zero QH50V.
* Car.
no2zero QH50W.
* Water pump.
no2zero QH50X.
* Thresher.
no2zero QH50Y.
* Tractor.
no2zero QH50Z.

* Type of cooking fuel.
dichotomize (QH51=1) QH51_1 "Type of cooking fuel: Electricity".
dichotomize (QH51=2) QH51_2 "Type of cooking fuel: LPG / natural gas".
dichotomize (QH51=3) QH51_3 "Type of cooking fuel: Biogas".
dichotomize (QH51=4) QH51_4 "Type of cooking fuel: Kerosene".
dichotomize (QH51=5) QH51_5 "Type of cooking fuel: Coal / lignite".
dichotomize (QH51=6) QH51_6 "Type of cooking fuel: Charcoal".
dichotomize (QH51=7) QH51_7 "Type of cooking fuel: Wood".
dichotomize (QH51=8) QH51_8 "Type of cooking fuel: Straw / shrubs / grass".
dichotomize (QH51=9) QH51_9 "Type of cooking fuel: Agricultural crop waste".
dichotomize (QH51=10) QH51_10 "Type of cooking fuel: Dung cakes".
dichotomize (QH51=95) QH51_95 "Type of cooking fuel: No food cooked in household".
dichotomize (QH51=96) QH51_96 "Type of cooking fuel: Other".


* Main material of floor.
dichotomize (QH57=11) QH57_11 "Main material of floor: Mud / clay / earth".
dichotomize (QH57=12) QH57_12 "Main material of floor: Sand".
dichotomize (QH57=13) QH57_13 "Main material of floor: Dung".
dichotomize (QH57=21) QH57_21 "Main material of floor: Raw wood planks".
dichotomize (QH57=22) QH57_22 "Main material of floor: Palm / bamboo".
dichotomize (QH57=23) QH57_23 "Main material of floor: Brick".
dichotomize (QH57=24) QH57_24 "Main material of floor: Stone".
dichotomize (QH57=31) QH57_31 "Main material of floor: Parquet / polished wood".
dichotomize (QH57=32) QH57_32 "Main material of floor: Vinyl / asphalt".
dichotomize (QH57=33) QH57_33 "Main material of floor: Ceramic tiles".
dichotomize (QH57=34) QH57_34 "Main material of floor: Cement".
dichotomize (QH57=35) QH57_35 "Main material of floor: Carpet".
dichotomize (QH57=36) QH57_36 "Main material of floor: Polished stone / marble / granite".
dichotomize (QH57=96) QH57_96 "Main material of floor: Other".


* Main roof material.
dichotomize (QH58=11) QH58_11 "Main roof material: No roof".
dichotomize (QH58=12) QH58_12 "Main roof material: Thatch / palm leaf / reed / grass".
dichotomize (QH58=13) QH58_13 "Main roof material: Mud".
dichotomize (QH58=14) QH58_14 "Main roof material: Sod / mud and grass mixture".
dichotomize (QH58=15) QH58_15 "Main roof material: Plastic / polythene sheeting".
dichotomize (QH58=21) QH58_21 "Main roof material: Rustic mat".
dichotomize (QH58=22) QH58_22 "Main roof material: Palm / bamboo".
dichotomize (QH58=23) QH58_23 "Main roof material: Raw wood planks / timber".
dichotomize (QH58=24) QH58_24 "Main roof material: Unburnt brick".
dichotomize (QH58=25) QH58_25 "Main roof material: Loosely packed stone".
dichotomize (QH58=31) QH58_31 "Main roof material: Metal / GI".
dichotomize (QH58=32) QH58_32 "Main roof material: Wood".
dichotomize (QH58=33) QH58_33 "Main roof material: Calamine / cement fiber".
dichotomize (QH58=34) QH58_34 "Main roof material: Asbestos sheets".
dichotomize (QH58=35) QH58_35 "Main roof material: RCC / RBC / cement / concrete".
dichotomize (QH58=36) QH58_36 "Main roof material: Roofing shingles".
dichotomize (QH58=37) QH58_37 "Main roof material: Tiles".
dichotomize (QH58=38) QH58_38 "Main roof material: Slate".
dichotomize (QH58=39) QH58_39 "Main roof material: Burnt brick".
dichotomize (QH58=96) QH58_96 "Main roof material: Other".


* Main wall material.
dichotomize (QH59=11) QH59_11 "Main wall material: No walls".
dichotomize (QH59=12) QH59_12 "Main wall material: Cane / palm / trunks / bamboo".
dichotomize (QH59=13) QH59_13 "Main wall material: Mud".
dichotomize (QH59=14) QH59_14 "Main wall material: Grass / reeds / thatch".
dichotomize (QH59=21) QH59_21 "Main wall material: Bamboo with mud".
dichotomize (QH59=22) QH59_22 "Main wall material: Stone with mud".
dichotomize (QH59=23) QH59_23 "Main wall material: Plywood".
dichotomize (QH59=24) QH59_24 "Main wall material: Cardboard".
dichotomize (QH59=25) QH59_25 "Main wall material: Unburnt brick".
dichotomize (QH59=26) QH59_26 "Main wall material: Raw wood / reused wood".
dichotomize (QH59=31) QH59_31 "Main wall material: Cement / concrete".
dichotomize (QH59=32) QH59_32 "Main wall material: Stone with lime / cement".
dichotomize (QH59=33) QH59_33 "Main wall material: Burnt bricks".
dichotomize (QH59=34) QH59_34 "Main wall material: Cement blocks".
dichotomize (QH59=35) QH59_35 "Main wall material: Wood planks / shingles".
dichotomize (QH59=36) QH59_36 "Main wall material: GI/  metal / asbestos sheets".
dichotomize (QH59=96) QH59_96 "Main wall material: Other".


* Acres for agricultural land.
compute landarea = QH65.
if (missing(QH65) | QH65 >= 999.8) landarea = 999.9.
if (missing(QH63) | QH63 <> 1) landarea=0.
missing values landarea (999.9).

* Cows / bulls / buffaloes / yaks.
no2zero QH67A.
* Camels.
no2zero QH67B.
* Horses / donkeys / mules.
no2zero QH67C.
* Goats.
no2zero QH67D.
* Sheep.
no2zero QH67E.
* Chickens / ducks.
no2zero QH67F.
* Bank account.
no2zero QH70.
*{Members per sleeping room}.
if (hhusual=0) hhusual=hhslept.
if (QH60>0) memsleep=trunc(hhusual/QH60).
if (QH60=0) memsleep=hhusual.
if (missing(QH60) or QH60>=99 or memsleep>=98) memsleep=99.
variable labels memsleep 'Number of members per sleeping room'.
value labels memsleep 0 'Less than 1 per room'.
formats memsleep (f2.0).
missing values memsleep (99).

* Compute urban and rural variables coded (1/0) for filters later.
compute urban=(QHTYPE = 1).
compute rural=(QHTYPE = 2).
variable labels urban 'Urban' / rural 'Rural'.
value labels urban 1 'Urban' / rural 1 'Rural'.
formats urban rural (f1.0).

execute.

* Check on indicator variable creation.
frequencies variables=QHTYPE to memsleep.

* Toilet facility by shared/not shared.
crosstabs /tables=QH40 by QH42.

frequencies variables=
  QH34_11 QH34_12 QH34_13 QH34_14 QH34_21 QH34_31 QH34_32 QH34_41 QH34_42 QH34_51 QH34_61 QH34_71 QH34_81 QH34_91 QH34_92 QH34_96
  QH40_11 QH40_12 QH40_13 QH40_14 QH40_15 QH40_21 QH40_22 QH40_23 QH40_31 QH40_41 QH40_51 QH40_96
  QH40_11_sh QH40_12_sh QH40_13_sh QH40_14_sh QH40_15_sh QH40_21_sh QH40_22_sh QH40_23_sh QH40_31_sh QH40_41_sh QH40_96_sh
  QH46_1 QH46_2 QH46_3 QH46_4
  QH50A QH50B QH50C QH50D QH50E QH50F QH50G QH50H QH50I QH50J QH50K QH50L QH50M QH50N QH50O QH50P QH50Q QH50R QH50S QH50T QH50U QH50V QH50W QH50X QH50Y QH50Z
  QH51_1 QH51_2 QH51_3 QH51_4 QH51_5 QH51_6 QH51_7 QH51_8 QH51_9 QH51_10 QH51_95 QH51_96
  QH57_11 QH57_12 QH57_13 QH57_21 QH57_22 QH57_23 QH57_24 QH57_31 QH57_32 QH57_33 QH57_34 QH57_35 QH57_36 QH57_96
  QH58_11 QH58_12 QH58_13 QH58_14 QH58_15 QH58_21 QH58_22 QH58_23 QH58_24 QH58_25 QH58_31 QH58_32 QH58_33 QH58_34 QH58_35 QH58_36 QH58_37 QH58_38 QH58_39
  QH58_96 QH59_11 QH59_12 QH59_13 QH59_14 QH59_21 QH59_22 QH59_23 QH59_24 QH59_25 QH59_26 QH59_31 QH59_32 QH59_33 QH59_34 QH59_35 QH59_36 QH59_96
  QH67A QH67B QH67C QH67D QH67E QH67F QH70 DOMESTIC DOMESTHH HOUSE LAND memsleep
  landarea
.

* Turn off weights before all factor analysis.
weight off.

* Name the dataset window for the HH data for use later.
dataset name assets.

save outfile='assets.sav'.

*** Test Factor Analysis.
filter off.
execute.

* Excluded Domestic, landarea.
factor /variables
  QH34_11 QH34_12 QH34_13 QH34_14 QH34_21 QH34_31 QH34_32 QH34_41 QH34_42 QH34_51 QH34_61 QH34_71 QH34_81 QH34_91 QH34_92 QH34_96
  QH40_11 QH40_12 QH40_13 QH40_14 QH40_15 QH40_21 QH40_22 QH40_23 QH40_31 QH40_41 QH40_51 QH40_96
  QH40_11_sh QH40_12_sh QH40_13_sh QH40_14_sh QH40_15_sh QH40_21_sh QH40_22_sh QH40_23_sh QH40_31_sh QH40_41_sh QH40_96_sh
  QH46_1 QH46_2 QH46_3 QH46_4
  QH50A QH50B QH50C QH50D QH50E QH50F QH50G QH50H QH50I QH50J QH50K QH50L QH50M QH50N QH50O QH50P QH50Q QH50R QH50S QH50T QH50U QH50V QH50W QH50X QH50Y QH50Z
  QH51_1 QH51_2 QH51_3 QH51_4 QH51_5 QH51_6 QH51_7 QH51_8 QH51_9 QH51_10 QH51_95 QH51_96
  QH57_11 QH57_12 QH57_13 QH57_21 QH57_22 QH57_23 QH57_24 QH57_31 QH57_32 QH57_33 QH57_34 QH57_35 QH57_36 QH57_96
  QH58_11 QH58_12 QH58_13 QH58_14 QH58_15 QH58_21 QH58_22 QH58_23 QH58_24 QH58_25 QH58_31 QH58_32 QH58_33 QH58_34 QH58_35 QH58_36 QH58_37 QH58_38 QH58_39
  QH58_96 QH59_11 QH59_12 QH59_13 QH59_14 QH59_21 QH59_22 QH59_23 QH59_24 QH59_25 QH59_26 QH59_31 QH59_32 QH59_33 QH59_34 QH59_35 QH59_36 QH59_96
  QH67A QH67B QH67C QH67D QH67E QH67F QH70 DOMESTHH HOUSE LAND memsleep
  /missing meansub
  /analysis
  QH34_11 QH34_12 QH34_13 QH34_14 QH34_21 QH34_31 QH34_32 QH34_41 QH34_42 QH34_51 QH34_61 QH34_71 QH34_81 QH34_91 QH34_92 QH34_96
  QH40_11 QH40_12 QH40_13 QH40_14 QH40_15 QH40_21 QH40_22 QH40_23 QH40_31 QH40_41 QH40_51 QH40_96
  QH40_11_sh QH40_12_sh QH40_13_sh QH40_14_sh QH40_15_sh QH40_21_sh QH40_22_sh QH40_23_sh QH40_31_sh QH40_41_sh QH40_96_sh
  QH46_1 QH46_2 QH46_3 QH46_4
  QH50A QH50B QH50C QH50D QH50E QH50F QH50G QH50H QH50I QH50J QH50K QH50L QH50M QH50N QH50O QH50P QH50Q QH50R QH50S QH50T QH50U QH50V QH50W QH50X QH50Y QH50Z
  QH51_1 QH51_2 QH51_3 QH51_4 QH51_5 QH51_6 QH51_7 QH51_8 QH51_9 QH51_10 QH51_95 QH51_96
  QH57_11 QH57_12 QH57_13 QH57_21 QH57_22 QH57_23 QH57_24 QH57_31 QH57_32 QH57_33 QH57_34 QH57_35 QH57_36 QH57_96
  QH58_11 QH58_12 QH58_13 QH58_14 QH58_15 QH58_21 QH58_22 QH58_23 QH58_24 QH58_25 QH58_31 QH58_32 QH58_33 QH58_34 QH58_35 QH58_36 QH58_37 QH58_38 QH58_39
  QH58_96 QH59_11 QH59_12 QH59_13 QH59_14 QH59_21 QH59_22 QH59_23 QH59_24 QH59_25 QH59_26 QH59_31 QH59_32 QH59_33 QH59_34 QH59_35 QH59_36 QH59_96
  QH67A QH67B QH67C QH67D QH67E QH67F QH70 DOMESTHH HOUSE LAND memsleep
  /print univariate initial extraction fscore
  /criteria factors(1) iterate(25)
  /extraction pc
  /rotation norotate
  /method=correlation.

*** Common Factor analysis ***.
** Removed area-specific variables **.
** Agricultural animal variables excluded
** Land area excluded
** Any others ?.

*** Common Factor Analysis.
filter off.
execute.

* Excluded Domestic, landarea.
factor /variables
  QH34_11 QH34_12 QH34_13 QH34_14 QH34_21 QH34_31 QH34_32 QH34_41 QH34_42 QH34_51 QH34_61 QH34_71 QH34_81 QH34_91 QH34_92 QH34_96
  QH40_11 QH40_12 QH40_13 QH40_14 QH40_15 QH40_21 QH40_22 QH40_23 QH40_31 QH40_41 QH40_51 QH40_96
  QH40_11_sh QH40_12_sh QH40_13_sh QH40_14_sh QH40_15_sh QH40_21_sh QH40_22_sh QH40_23_sh QH40_31_sh QH40_41_sh QH40_96_sh
  QH46_1 QH46_2 QH46_3 QH46_4
  QH50A QH50B QH50C QH50D QH50E QH50F QH50G QH50H QH50I QH50J QH50K QH50L QH50M QH50N QH50O QH50P QH50Q QH50R QH50S QH50T QH50U QH50V QH50W QH50X QH50Y QH50Z
  QH51_1 QH51_2 QH51_3 QH51_4 QH51_5 QH51_6 QH51_7 QH51_8 QH51_9 QH51_10 QH51_95 QH51_96
  QH57_11 QH57_12 QH57_13 QH57_21 QH57_22 QH57_23 QH57_24 QH57_31 QH57_32 QH57_33 QH57_34 QH57_35 QH57_36 QH57_96
  QH58_11 QH58_12 QH58_13 QH58_14 QH58_15 QH58_21 QH58_22 QH58_23 QH58_24 QH58_25 QH58_31 QH58_32 QH58_33 QH58_34 QH58_35 QH58_36 QH58_37 QH58_38 QH58_39
  QH58_96 QH59_11 QH59_12 QH59_13 QH59_14 QH59_21 QH59_22 QH59_23 QH59_24 QH59_25 QH59_26 QH59_31 QH59_32 QH59_33 QH59_34 QH59_35 QH59_36 QH59_96
  QH67A QH67B QH67C QH67D QH67E QH67F QH70 DOMESTHH HOUSE LAND memsleep
  /missing meansub
  /analysis
  QH34_11 QH34_12 QH34_13 QH34_14 QH34_21 QH34_31 QH34_32 QH34_41 QH34_42 QH34_51 QH34_61 QH34_71 QH34_81 QH34_91 QH34_92 QH34_96
  QH40_11 QH40_12 QH40_13 QH40_14 QH40_15 QH40_21 QH40_22 QH40_23 QH40_31 QH40_41 QH40_51 QH40_96
  QH40_11_sh QH40_12_sh QH40_13_sh QH40_14_sh QH40_15_sh QH40_21_sh QH40_22_sh QH40_23_sh QH40_31_sh QH40_41_sh QH40_96_sh
  QH46_1 QH46_2 QH46_3 QH46_4
  QH50A QH50B QH50C QH50D QH50E QH50F QH50G QH50H QH50I QH50J QH50K QH50L QH50M QH50N QH50O QH50P QH50Q QH50R QH50S QH50T QH50U QH50V QH50W QH50X QH50Y QH50Z
  QH51_1 QH51_2 QH51_3 QH51_4 QH51_5 QH51_6 QH51_7 QH51_8 QH51_9 QH51_10 QH51_95 QH51_96
  QH57_11 QH57_12 QH57_13 QH57_21 QH57_22 QH57_23 QH57_24 QH57_31 QH57_32 QH57_33 QH57_34 QH57_35 QH57_36 QH57_96
  QH58_11 QH58_12 QH58_13 QH58_14 QH58_15 QH58_21 QH58_22 QH58_23 QH58_24 QH58_25 QH58_31 QH58_32 QH58_33 QH58_34 QH58_35 QH58_36 QH58_37 QH58_38 QH58_39
  QH58_96 QH59_11 QH59_12 QH59_13 QH59_14 QH59_21 QH59_22 QH59_23 QH59_24 QH59_25 QH59_26 QH59_31 QH59_32 QH59_33 QH59_34 QH59_35 QH59_36 QH59_96
  QH67A QH67B QH67C QH67D QH67E QH67F QH70 DOMESTHH HOUSE LAND memsleep
  /print univariate initial extraction fscore
  /criteria factors(1) iterate(25)
  /extraction pc
  /rotation norotate
  /save reg(ALL com)
  /method=correlation.

*** Urban Factor Analysis.
filter off.
filter by urban.
execute.

* Excluded Domestic, landarea.
factor /variables
  QH34_11 QH34_12 QH34_13 QH34_14 QH34_21 QH34_31 QH34_32 QH34_41 QH34_42 QH34_51 QH34_61 QH34_71 QH34_81 QH34_91 QH34_92 QH34_96
  QH40_11 QH40_12 QH40_13 QH40_14 QH40_15 QH40_21 QH40_22 QH40_23 QH40_31 QH40_41 QH40_51 QH40_96
  QH40_11_sh QH40_12_sh QH40_13_sh QH40_14_sh QH40_15_sh QH40_21_sh QH40_22_sh QH40_23_sh QH40_31_sh QH40_41_sh QH40_96_sh
  QH46_1 QH46_2 QH46_3 QH46_4
  QH50A QH50B QH50C QH50D QH50E QH50F QH50G QH50H QH50I QH50J QH50K QH50L QH50M QH50N QH50O QH50P QH50Q QH50R QH50S QH50T QH50U QH50V QH50W QH50X QH50Y QH50Z
  QH51_1 QH51_2 QH51_3 QH51_4 QH51_5 QH51_6 QH51_7 QH51_8 QH51_9 QH51_10 QH51_95 QH51_96
  QH57_11 QH57_12 QH57_13 QH57_21 QH57_22 QH57_23 QH57_24 QH57_31 QH57_32 QH57_33 QH57_34 QH57_35 QH57_36 QH57_96
  QH58_11 QH58_12 QH58_13 QH58_14 QH58_15 QH58_21 QH58_22 QH58_23 QH58_24 QH58_25 QH58_31 QH58_32 QH58_33 QH58_34 QH58_35 QH58_36 QH58_37 QH58_38 QH58_39
  QH58_96 QH59_11 QH59_12 QH59_13 QH59_14 QH59_21 QH59_22 QH59_23 QH59_24 QH59_25 QH59_26 QH59_31 QH59_32 QH59_33 QH59_34 QH59_35 QH59_36 QH59_96
  QH67A QH67B QH67C QH67D QH67E QH67F QH70 DOMESTHH HOUSE LAND memsleep
  /missing meansub
  /analysis
  QH34_11 QH34_12 QH34_13 QH34_14 QH34_21 QH34_31 QH34_32 QH34_41 QH34_42 QH34_51 QH34_61 QH34_71 QH34_81 QH34_91 QH34_92 QH34_96
  QH40_11 QH40_12 QH40_13 QH40_14 QH40_15 QH40_21 QH40_22 QH40_23 QH40_31 QH40_41 QH40_51 QH40_96
  QH40_11_sh QH40_12_sh QH40_13_sh QH40_14_sh QH40_15_sh QH40_21_sh QH40_22_sh QH40_23_sh QH40_31_sh QH40_41_sh QH40_96_sh
  QH46_1 QH46_2 QH46_3 QH46_4
  QH50A QH50B QH50C QH50D QH50E QH50F QH50G QH50H QH50I QH50J QH50K QH50L QH50M QH50N QH50O QH50P QH50Q QH50R QH50S QH50T QH50U QH50V QH50W QH50X QH50Y QH50Z
  QH51_1 QH51_2 QH51_3 QH51_4 QH51_5 QH51_6 QH51_7 QH51_8 QH51_9 QH51_10 QH51_95 QH51_96
  QH57_11 QH57_12 QH57_13 QH57_21 QH57_22 QH57_23 QH57_24 QH57_31 QH57_32 QH57_33 QH57_34 QH57_35 QH57_36 QH57_96
  QH58_11 QH58_12 QH58_13 QH58_14 QH58_15 QH58_21 QH58_22 QH58_23 QH58_24 QH58_25 QH58_31 QH58_32 QH58_33 QH58_34 QH58_35 QH58_36 QH58_37 QH58_38 QH58_39
  QH58_96 QH59_11 QH59_12 QH59_13 QH59_14 QH59_21 QH59_22 QH59_23 QH59_24 QH59_25 QH59_26 QH59_31 QH59_32 QH59_33 QH59_34 QH59_35 QH59_36 QH59_96
  QH67A QH67B QH67C QH67D QH67E QH67F QH70 DOMESTHH HOUSE LAND memsleep
  /print univariate initial extraction fscore
  /criteria factors(1) iterate(25)
  /extraction pc
  /rotation norotate
  /save reg(ALL urb)
  /method=correlation.

*** Rural Factor Analysis.
filter off.
filter by rural.
execute.

* Excluded Domestic, landarea.
factor /variables
  QH34_11 QH34_12 QH34_13 QH34_14 QH34_21 QH34_31 QH34_32 QH34_41 QH34_42 QH34_51 QH34_61 QH34_71 QH34_81 QH34_91 QH34_92 QH34_96
  QH40_11 QH40_12 QH40_13 QH40_14 QH40_15 QH40_21 QH40_22 QH40_23 QH40_31 QH40_41 QH40_51 QH40_96
  QH40_11_sh QH40_12_sh QH40_13_sh QH40_14_sh QH40_15_sh QH40_21_sh QH40_22_sh QH40_23_sh QH40_31_sh QH40_41_sh QH40_96_sh
  QH46_1 QH46_2 QH46_3 QH46_4
  QH50A QH50B QH50C QH50D QH50E QH50F QH50G QH50H QH50I QH50J QH50K QH50L QH50M QH50N QH50O QH50P QH50Q QH50R QH50S QH50T QH50U QH50V QH50W QH50X QH50Y QH50Z
  QH51_1 QH51_2 QH51_3 QH51_4 QH51_5 QH51_6 QH51_7 QH51_8 QH51_9 QH51_10 QH51_95 QH51_96
  QH57_11 QH57_12 QH57_13 QH57_21 QH57_22 QH57_23 QH57_24 QH57_31 QH57_32 QH57_33 QH57_34 QH57_35 QH57_36 QH57_96
  QH58_11 QH58_12 QH58_13 QH58_14 QH58_15 QH58_21 QH58_22 QH58_23 QH58_24 QH58_25 QH58_31 QH58_32 QH58_33 QH58_34 QH58_35 QH58_36 QH58_37 QH58_38 QH58_39
  QH58_96 QH59_11 QH59_12 QH59_13 QH59_14 QH59_21 QH59_22 QH59_23 QH59_24 QH59_25 QH59_26 QH59_31 QH59_32 QH59_33 QH59_34 QH59_35 QH59_36 QH59_96
  QH67A QH67B QH67C QH67D QH67E QH67F QH70 DOMESTHH HOUSE LAND memsleep
  /missing meansub
  /analysis
  QH34_11 QH34_12 QH34_13 QH34_14 QH34_21 QH34_31 QH34_32 QH34_41 QH34_42 QH34_51 QH34_61 QH34_71 QH34_81 QH34_91 QH34_92 QH34_96
  QH40_11 QH40_12 QH40_13 QH40_14 QH40_15 QH40_21 QH40_22 QH40_23 QH40_31 QH40_41 QH40_51 QH40_96
  QH40_11_sh QH40_12_sh QH40_13_sh QH40_14_sh QH40_15_sh QH40_21_sh QH40_22_sh QH40_23_sh QH40_31_sh QH40_41_sh QH40_96_sh
  QH46_1 QH46_2 QH46_3 QH46_4
  QH50A QH50B QH50C QH50D QH50E QH50F QH50G QH50H QH50I QH50J QH50K QH50L QH50M QH50N QH50O QH50P QH50Q QH50R QH50S QH50T QH50U QH50V QH50W QH50X QH50Y QH50Z
  QH51_1 QH51_2 QH51_3 QH51_4 QH51_5 QH51_6 QH51_7 QH51_8 QH51_9 QH51_10 QH51_95 QH51_96
  QH57_11 QH57_12 QH57_13 QH57_21 QH57_22 QH57_23 QH57_24 QH57_31 QH57_32 QH57_33 QH57_34 QH57_35 QH57_36 QH57_96
  QH58_11 QH58_12 QH58_13 QH58_14 QH58_15 QH58_21 QH58_22 QH58_23 QH58_24 QH58_25 QH58_31 QH58_32 QH58_33 QH58_34 QH58_35 QH58_36 QH58_37 QH58_38 QH58_39
  QH58_96 QH59_11 QH59_12 QH59_13 QH59_14 QH59_21 QH59_22 QH59_23 QH59_24 QH59_25 QH59_26 QH59_31 QH59_32 QH59_33 QH59_34 QH59_35 QH59_36 QH59_96
  QH67A QH67B QH67C QH67D QH67E QH67F QH70 DOMESTHH HOUSE LAND memsleep
  /print univariate initial extraction fscore
  /criteria factors(1) iterate(25)
  /extraction pc
  /rotation norotate
  /save reg(ALL rur)
  /method=correlation.

* Label the created score variables.
rename variables (com1 urb1 rur1=comscore urbscore rurscore).
variable labels comscore 'Common wealth score' /urbscore 'Urban wealth score' /rurscore 'Rural wealth score'.

* Add a variable used for linking later.
filter off.
string rowtype_ (A8).
compute rowtype_ = 'EST'.

* Calculate regressions.
** Area=urban.
filter off.
filter by urban.
execute.

* Declare a dataset to be written to in the regression.
dataset declare urbancorv.
* Run regression of comscore with urbscore.
regression
  /missing listwise
  /statistics coeff outs R anova
  /criteria=pin(.05) pout(.10)
  /noorigin
  /dependent comscore
  /method=enter urbscore
  /outfile=corv(urbancorv).

* Activate file of output from regression.
dataset activate urbancorv.
* Drop all rows of output except the coefficients.
select if (rowtype_ = 'EST').
execute.
* Delete unnecessary variables before merging.
delete variables DEPVAR_ VARNAME_.
* Rename variables containing the constant and the coefficient.
rename variables CONST_=urbconst urbscore=urbcoeff.

* Re-activate the main household data.
dataset activate assets.
* merge the coefficients.
match files /file = *
  /table = urbancorv
  /by ROWTYPE_.
execute.

* Calculate regressions.
** Area=rural.
filter off.
filter by rural.
execute.

* Declare a dataset to be written to in the regression.
dataset declare ruralcorv.
* Run regression of comscore with rurscore.
regression
  /missing listwise
  /statistics coeff outs R anova
  /criteria=pin(.05) pout(.10)
  /noorigin
  /dependent comscore
  /method=enter rurscore
  /outfile=corv(ruralcorv).

* Activate file of output from regression.
dataset activate ruralcorv.
* Drop all rows of output except the coefficients.
select if (rowtype_ = 'EST').
execute.
* Delete unnecessary variables before merging.
delete variables DEPVAR_ VARNAME_.
* Rename variables containing the constant and the coefficient.
rename variables CONST_=rurconst rurscore=rurcoeff.

* Re-activate the main household data.
dataset activate assets.
* merge the coefficients.
match files /file = *
  /table = ruralcorv
  /by ROWTYPE_.
execute.

dataset close urbancorv.
dataset close ruralcorv.
dataset activate assets.
filter off.

*** Calculate combined wealth score from Urban and Rural Scores.
* Use coefficients from urban and rural regressions above.
compute combscor=0.
print formats combscor (f11.5).
write formats combscor (f11.5).
** Urban.
if (urban = 1) combscor=urbconst+urbcoeff*urbscore.
** Rural.
if (rural = 1) combscor=rurconst+rurcoeff*rurscore.
variable labels combscor 'Combined national wealth score'.
execute.

* Switch to QHWEIGHTN for national.
*compute hhwt = QHWEIGHT/1000000.
compute hhwt = QHWEIGHTN/1000000.
variable labels hhwt 'HH weights'.
formats hhwt (f12.6).
weight by hhwt.

filter off.
execute.

frequencies variables=combscor comscore
  /format=notable
  /ntiles=5
  /statistics=minimum maximum stddev mean
  /histogram normal
  /order=analysis.

filter off.
filter by urban.
execute.

frequencies variables=combscor urbscore
  /format=notable
  /ntiles=5
  /statistics=minimum maximum stddev mean
  /histogram normal
  /order=analysis.

filter off.
filter by rural.
execute.

frequencies variables=combscor rurscore
  /format=notable
  /ntiles=5
  /statistics=minimum maximum stddev mean
  /histogram normal
  /order=analysis.

filter off.
execute.

*Calculate quintiles and scores for data file.
*Switch to QHWEIGHTN for national.
*compute hhmemwt=QHWEIGHT*hhusual/1000000.
compute hhmemwt=QHWEIGHTN*hhusual/1000000.
variable labels hhmemwt 'HH members weighting for index'.
formats hhmemwt (f12.6).
weight by hhmemwt.

filter off.
filter by urban.
execute.

rank variables=urbscore (A) /rank /ntiles (5) /print=yes /ties=mean.
rank variables=urbscore (A) by QHSTATE /rank /ntiles (5) /print=yes /ties=mean.

filter off.
filter by rural.
execute.

rank variables=rurscore (A) /rank /ntiles (5) /print=yes /ties=mean.
rank variables=rurscore (A) by QHSTATE /rank /ntiles (5) /print=yes /ties=mean.

filter off.
execute.

rank variables=combscor (A) /rank /ntiles (5) /print=yes /ties=mean.
rank variables=combscor (A) by QHSTATE /rank /ntiles (5) /print=yes /ties=mean.

delete variables RAN001 RAN002 RAN003.
rename variables NTI001=Nurb_s NTI002=Nrur_s NTI003=Ncomb_s.

variable labels ncombsco 'Combined wealth index' /nurbscor 'Urban wealth index' /nrurscor 'Rural wealth index'
  ncomb_s 'Combined wealth index within state' /nurb_s 'Urban wealth index within state' /nrur_s 'Rural wealth index within state'.
value labels ncombsco nurbscor nrurscor ncomb_s nurb_s nrur_s 1 'Lowest' 2 'Second' 3 'Middle' 4 'Fourth' 5 'Highest'.

crosstabs /tables=QHSTATE by ncombsco /cells=count row /count=asis.

*** Check on quintiles.
frequencies variables=ncombsco nurbscor nrurscor ncomb_s nurb_s nrur_s.

weight by hhwt.

* Exclude domestic landarea.
ctables /table (
  QH34_11+QH34_12+QH34_13+QH34_14+QH34_21+QH34_31+QH34_32+QH34_41+QH34_42+QH34_51+QH34_61+QH34_71+QH34_81+QH34_91+QH34_92+QH34_96+
  QH40_11+QH40_12+QH40_13+QH40_14+QH40_15+QH40_21+QH40_22+QH40_23+QH40_31+QH40_41+QH40_51+QH40_96+
  QH40_11_sh+QH40_12_sh+QH40_13_sh+QH40_14_sh+QH40_15_sh+QH40_21_sh+QH40_22_sh+QH40_23_sh+QH40_31_sh+QH40_41_sh+QH40_96_sh+
  QH46_1+QH46_2+QH46_3+QH46_4+
  QH50A+QH50B+QH50C+QH50D+QH50E+QH50F+QH50G+QH50H+QH50I+QH50J+QH50K+QH50L+QH50M+QH50N+QH50O+QH50P+QH50Q+QH50R+QH50S+QH50T+QH50U+QH50V+QH50W+QH50X+QH50Y+QH50Z+
  QH51_1+QH51_2+QH51_3+QH51_4+QH51_5+QH51_6+QH51_7+QH51_8+QH51_9+QH51_10+QH51_95+QH51_96+
  QH57_11+QH57_12+QH57_13+QH57_21+QH57_22+QH57_23+QH57_24+QH57_31+QH57_32+QH57_33+QH57_34+QH57_35+QH57_36+QH57_96+
  QH58_11+QH58_12+QH58_13+QH58_14+QH58_15+QH58_21+QH58_22+QH58_23+QH58_24+QH58_25+QH58_31+QH58_32+QH58_33+QH58_34+QH58_35+QH58_36+QH58_37+QH58_38+QH58_39+
  QH58_96+QH59_11+QH59_12+QH59_13+QH59_14+QH59_21+QH59_22+QH59_23+QH59_24+QH59_25+QH59_26+QH59_31+QH59_32+QH59_33+QH59_34+QH59_35+QH59_36+QH59_96+
  QH67A+QH67B+QH67C+QH67D+QH67E+QH67F+QH70+DOMESTHH+HOUSE+LAND+memsleep
  )[S][Mean F8.3] by (ncombsco+nurbscor+nrurscor)[C]
  /slabels visible=no.

* For state quintiles.
* Exclude domestic landarea.
ctables /table (
  QH34_11+QH34_12+QH34_13+QH34_14+QH34_21+QH34_31+QH34_32+QH34_41+QH34_42+QH34_51+QH34_61+QH34_71+QH34_81+QH34_91+QH34_92+QH34_96+
  QH40_11+QH40_12+QH40_13+QH40_14+QH40_15+QH40_21+QH40_22+QH40_23+QH40_31+QH40_41+QH40_51+QH40_96+
  QH40_11_sh+QH40_12_sh+QH40_13_sh+QH40_14_sh+QH40_15_sh+QH40_21_sh+QH40_22_sh+QH40_23_sh+QH40_31_sh+QH40_41_sh+QH40_96_sh+
  QH46_1+QH46_2+QH46_3+QH46_4+
  QH50A+QH50B+QH50C+QH50D+QH50E+QH50F+QH50G+QH50H+QH50I+QH50J+QH50K+QH50L+QH50M+QH50N+QH50O+QH50P+QH50Q+QH50R+QH50S+QH50T+QH50U+QH50V+QH50W+QH50X+QH50Y+QH50Z+
  QH51_1+QH51_2+QH51_3+QH51_4+QH51_5+QH51_6+QH51_7+QH51_8+QH51_9+QH51_10+QH51_95+QH51_96+
  QH57_11+QH57_12+QH57_13+QH57_21+QH57_22+QH57_23+QH57_24+QH57_31+QH57_32+QH57_33+QH57_34+QH57_35+QH57_36+QH57_96+
  QH58_11+QH58_12+QH58_13+QH58_14+QH58_15+QH58_21+QH58_22+QH58_23+QH58_24+QH58_25+QH58_31+QH58_32+QH58_33+QH58_34+QH58_35+QH58_36+QH58_37+QH58_38+QH58_39+
  QH58_96+QH59_11+QH59_12+QH59_13+QH59_14+QH59_21+QH59_22+QH59_23+QH59_24+QH59_25+QH59_26+QH59_31+QH59_32+QH59_33+QH59_34+QH59_35+QH59_36+QH59_96+
  QH67A+QH67B+QH67C+QH67D+QH67E+QH67F+QH70+DOMESTHH+HOUSE+LAND+memsleep
  )[S][Mean F8.3] by (ncomb_s+nurb_s+nrur_s)[C]
  /slabels visible=no.

* Exclude domestic landarea.
* Alternative instead of ctables.
*means tables=
  QH34_11 QH34_12 QH34_13 QH34_14 QH34_21 QH34_31 QH34_32 QH34_41 QH34_42 QH34_51 QH34_61 QH34_71 QH34_81 QH34_91 QH34_92 QH34_96
  QH40_11 QH40_12 QH40_13 QH40_14 QH40_15 QH40_21 QH40_22 QH40_23 QH40_31 QH40_41 QH40_51 QH40_96
  QH40_11_sh QH40_12_sh QH40_13_sh QH40_14_sh QH40_15_sh QH40_21_sh QH40_22_sh QH40_23_sh QH40_31_sh QH40_41_sh QH40_96_sh
  QH46_1 QH46_2 QH46_3 QH46_4
  QH50A QH50B QH50C QH50D QH50E QH50F QH50G QH50H QH50I QH50J QH50K QH50L QH50M QH50N QH50O QH50P QH50Q QH50R QH50S QH50T QH50U QH50V QH50W QH50X QH50Y QH50Z
  QH51_1 QH51_2 QH51_3 QH51_4 QH51_5 QH51_6 QH51_7 QH51_8 QH51_9 QH51_10 QH51_95 QH51_96
  QH57_11 QH57_12 QH57_13 QH57_21 QH57_22 QH57_23 QH57_24 QH57_31 QH57_32 QH57_33 QH57_34 QH57_35 QH57_36 QH57_96
  QH58_11 QH58_12 QH58_13 QH58_14 QH58_15 QH58_21 QH58_22 QH58_23 QH58_24 QH58_25 QH58_31 QH58_32 QH58_33 QH58_34 QH58_35 QH58_36 QH58_37 QH58_38 QH58_39
  QH58_96 QH59_11 QH59_12 QH59_13 QH59_14 QH59_21 QH59_22 QH59_23 QH59_24 QH59_25 QH59_26 QH59_31 QH59_32 QH59_33 QH59_34 QH59_35 QH59_36 QH59_96
  QH67A QH67B QH67C QH67D QH67E QH67F QH70  DOMESTHH HOUSE LAND memsleep
    by ncombsco nurbscor nrurscor
  /cells mean count stddev.

graph /histogram(normal)=combscor /title= 'Distribution of Households by Wealth Scores'.
frequencies variables=combscor
  /format=notable
  /ntiles=5
  /statistics=stddev minimum maximum semean mean median mode skewness seskew kurtosis sekurt
  /order=analysis.

weight off.
filter off.
write formats combscor urbscore rurscore (f11.5).

* Save final dataset of assets.
save outfile='assets.sav'.

*** Write out scores file.
write outfile='scores.dat' table /QHSTATE QHDIST QHPSU QHNUMBER combscor ncombsco ncomb_s urbscore nurbscor nurb_s rurscore nrurscor nrur_s.
execute.

* Produce table 2.6 weighted by de jure population to test.
weight by hhmemwt.
compute total = 0.
variable labels total 'Total'.
value labels total 0 ' '.
ctables /vlabels variables=QHSTATE QHTYPE total Ncombsco display=both
  /table QHSTATE [C] + QHTYPE [C] + total [C] BY Ncombsco [C][rowpct.count '%' F8.1, totals [rowpct.count '%' F8.1, count '' F8.0]]
  /categories variables=Ncombsco total=yes
  /titles title='Table 2.6 Wealth Quintiles' ''
    'Percent distribution of the de jure population by wealth quintiles, according to residence and region, India NFHS 2019-20'
  corner='Residence/region' /slabels visible=no.

ctables /vlabels variables=QHSTATE QHTYPE total Ncomb_s display=both
  /table QHSTATE [C] > (QHTYPE [C] + total [C]) + total [C] BY Ncomb_s [C][rowpct.count '%' F8.1, totals [rowpct.count '%' F8.1, count '' F8.0]]
  /categories variables=Ncomb_s total=yes
  /titles title='Table 2.6a State Wealth Quintiles' ''
    'Percent distribution of the de jure population by state wealth quintiles, according to residence and region, India NFHS 2019-20'
  corner='Residence/region' /slabels visible=no.