* Wealth index calculation. Rajendra Dangol, 01/05/2023. Bangladesh DHS 2022.
cd 'C:\Users\21180\ICF\Bangladesh DHS 2022 - DP\Wealth '.
include file='wealth_assets.sps'.
missing values QH131 QH131A (99.9).
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 (QH110=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 (QH101=11) QH101_11 "Source of drinking water: Piped into dwelling".
dichotomize (QH101=12) QH101_12 "Source of drinking water: Piped to yard/plot".
dichotomize (QH101=13) QH101_13 "Source of drinking water: Piped to neighbor".
dichotomize (QH101=14) QH101_14 "Source of drinking water: Public tap/standpipe".
dichotomize (QH101=21) QH101_21 "Source of drinking water: Tube well or borehole".
dichotomize (QH101=31) QH101_31 "Source of drinking water: Protected well".
dichotomize (QH101=32) QH101_32 "Source of drinking water: Unprotected well".
dichotomize (QH101=41) QH101_41 "Source of drinking water: Protected spring".
dichotomize (QH101=42) QH101_42 "Source of drinking water: Unprotected spring".
dichotomize (QH101=51) QH101_51 "Source of drinking water: Rainwater".
dichotomize (QH101=61) QH101_61 "Source of drinking water: Tanker truck".
dichotomize (QH101=71) QH101_71 "Source of drinking water: Cart with small tank".
dichotomize (QH101=81) QH101_81 "Source of drinking water: Surface water (river/dam/lake/pond/stream/canal/irrigation channel)".
dichotomize (QH101=91) QH101_91 "Source of drinking water: Bottled water".
dichotomize (QH101=96) QH101_96 "Source of drinking water: Other".


* Type of toilet facility.
dichotomize (QH109=11) QH109_11 "Type of toilet facility: Flush to piped sewer system".
dichotomize (QH109=12) QH109_12 "Type of toilet facility: Flush to septic tank".
dichotomize (QH109=13) QH109_13 "Type of toilet facility: Flush to pit latrine".
dichotomize (QH109=14) QH109_14 "Type of toilet facility: Flush to somewhere else".
dichotomize (QH109=15) QH109_15 "Type of toilet facility: Flush, don't know where".
dichotomize (QH109=21) QH109_21 "Type of toilet facility: Ventilated improved pit latrine".
dichotomize (QH109=22) QH109_22 "Type of toilet facility: Pit latrine with slab".
dichotomize (QH109=23) QH109_23 "Type of toilet facility: Pit latrine without slab/open pit".
*ichotomize (QH109=31) QH109_31 "Type of toilet facility: Composting toilet".
dichotomize (QH109=31 | QH109=41) QH109_41 "Type of toilet facility: Bucket toilet/composting toilet".
dichotomize (QH109=51) QH109_51 "Type of toilet facility: Hanging toilet/hanging latrine".
dichotomize (QH109=61) QH109_61 "Type of toilet facility: No facility/bush/field".
dichotomize (QH109=96) QH109_96 "Type of toilet facility: Other".

shared_fac QH109_11 QH109_11_sh "Type of toilet facility: Flush to piped sewer system - shared".
shared_fac QH109_12 QH109_12_sh "Type of toilet facility: Flush to septic tank - shared".
shared_fac QH109_13 QH109_13_sh "Type of toilet facility: Flush to pit latrine - shared".
shared_fac QH109_14 QH109_14_sh "Type of toilet facility: Flush to somewhere else - shared".
shared_fac QH109_15 QH109_15_sh "Type of toilet facility: Flush, don't know where - shared".
shared_fac QH109_21 QH109_21_sh "Type of toilet facility: Ventilated improved pit latrine - shared".
shared_fac QH109_22 QH109_22_sh "Type of toilet facility: Pit latrine with slab - shared".
shared_fac QH109_23 QH109_23_sh "Type of toilet facility: Pit latrine without slab/open pit - shared".
*hared_fac QH109_31 QH109_31_sh "Type of toilet facility: Composting toilet - shared".
shared_fac QH109_41 QH109_41_sh "Type of toilet facility: Bucket toilet/composting toilet - shared".
shared_fac QH109_51 QH109_51_sh "Type of toilet facility: Hanging toilet/hanging latrine - shared".
shared_fac QH109_96 QH109_96_sh "Type of toilet facility: Other - shared".


* Buffaloes.
if (missing(QH129A) | QH128 <> 1) QH129A=0.
missing values QH129A (99).
compute QH129A_1 = (QH129A >= 1 & QH129A <= 4).
compute QH129A_2 = (QH129A >= 5 & QH129A <= 9).
compute QH129A_3 = (QH129A >= 10 & QH129A <= 98).
variable labels QH129A_1 'Buffaloes: 1-4' /QH129A_2 'Buffaloes: 5-9' /QH129A_3 'Buffaloes: 10+'.


* Cows/bulls.
if (missing(QH129B) | QH128 <> 1) QH129B=0.
missing values QH129B (99).
compute QH129B_1 = (QH129B >= 1 & QH129B <= 4).
compute QH129B_2 = (QH129B >= 5 & QH129B <= 9).
compute QH129B_3 = (QH129B >= 10 & QH129B <= 98).
variable labels QH129B_1 'Cows/bulls: 1-4' /QH129B_2 'Cows/bulls: 5-9' /QH129B_3 'Cows/bulls: 10+'.


* Goats or sheeps.
if (missing(QH129C) | QH128 <> 1) QH129C=0.
missing values QH129C (99).
compute QH129C_1 = (QH129C >= 1 & QH129C <= 4).
compute QH129C_2 = (QH129C >= 5 & QH129C <= 9).
compute QH129C_3 = (QH129C >= 10 & QH129C <= 98).
variable labels QH129C_1 'Goats or sheeps: 1-4' /QH129C_2 'Goats or sheeps: 5-9' /QH129C_3 'Goats or sheeps: 10+'.


* Chickens or ducks.
if (missing(QH129D) | QH128 <> 1) QH129D=0.
missing values QH129D (99).
compute QH129D_1 = (QH129D >= 1 & QH129D <= 9).
compute QH129D_2 = (QH129D >= 10 & QH129D <= 29).
compute QH129D_3 = (QH129D >= 30 & QH129D <= 98).
variable labels QH129D_1 'Chickens or ducks: 1-9' /QH129D_2 'Chickens or ducks: 10-29' /QH129D_3 'Chickens or ducks: 30+'.


* Other farm animals.
if (missing(QH129E) | QH128 <> 1) QH129E=0.
missing values QH129E (99).
compute QH129E_1 = (QH129E >= 1 & QH129E <= 98).
*ompute QH129E_1 = (QH129E >= 1 & QH129E <= 4).
*ompute QH129E_2 = (QH129E >= 5 & QH129E <= 9).
*ompute QH129E_3 = (QH129E >= 10 & QH129E <= 98).
*ariable labels QH129E_1 'Other farm animals: 1-4' /QH129E_2 'Other farm animals: 5-9' /QH129E_3 'Other farm animals: 10+'.
variable labels QH129E_1 'Other farm animals: 1+'.


* Acres for agricultural land.
compute landarea = QH131A.
if (missing(QH131A) | QH131A >= 99.8) landarea = 99.9.
if (missing(QH130) | QH130 <> 1) landarea=0.
missing values landarea (99.9).


* Electricity.
no2zero QH132A.
* Radio.
no2zero QH132B.
* Television.
no2zero QH132C.
* Telephone (non-mobile).
no2zero QH132D.
* Computer.
no2zero QH132E.
* Refrigerator.
no2zero QH132F.
* Solar electricity - CS.
no2zero QH132G.
* Almirah/wardrobe  - CS.
no2zero QH132I.
* Electric fan  - CS.
no2zero QH132J.
* DVD/VCD player  - CS.
no2zero QH132K.
* Water pump  - CS.
no2zero QH132L.
* IPS/generator  - CS.
no2zero QH132M.
* Air conditioner  - CS.
no2zero QH132N.
* Car/truck/minibus.
no2zero QH133A.
* Autobike/tempo/CNG - CS.
no2zero QH133B.
* Rickshaw/van - CS.
no2zero QH133C.
* Bicycle.
no2zero QH133D.
* Motorcycle or scooter.
no2zero QH133E.
* Boat with a motor.
no2zero QH133F.
* Canoe/boat without motor.
no2zero QH133G.

* Main floor material.
dichotomize (QH152=11) QH152_11 "Main floor material: Earth/sand".
dichotomize (QH152=12) QH152_12 "Main floor material: Dung".
dichotomize (QH152=21) QH152_21 "Main floor material: Wood planks".
dichotomize (QH152=22) QH152_22 "Main floor material: Palm/bamboo".
dichotomize (QH152=31) QH152_31 "Main floor material: Parquet or polished wood".
dichotomize (QH152=32) QH152_32 "Main floor material: Vinyl or asphalt strips".
dichotomize (QH152=33) QH152_33 "Main floor material: Ceramic tiles".
dichotomize (QH152=34) QH152_34 "Main floor material: Cement".
dichotomize (QH152=35) QH152_35 "Main floor material: Carpet".
dichotomize (QH152=96) QH152_96 "Main floor material: Other".


* Main roof material.
dichotomize (QH153=11) QH153_11 "Main roof material: No roof".
dichotomize (QH153=12) QH153_12 "Main roof material: Thatch/palm leaf".
*ichotomize (QH153=13) QH153_13 "Main roof material: Sod".
dichotomize (QH153=21) QH153_21 "Main roof material: Rustic mat".
dichotomize (QH153=22) QH153_22 "Main roof material: Palm/bamboo".
dichotomize (QH153=23) QH153_23 "Main roof material: Wood planks".
*ichotomize (QH153=24) QH153_24 "Main roof material: Cardboard".
dichotomize (QH153=31) QH153_31 "Main roof material: Tin/Metal".
dichotomize (QH153=32) QH153_32 "Main roof material: Wood".
dichotomize (QH153=33) QH153_33 "Main roof material: Calamine/cement fiber".
dichotomize (QH153=34) QH153_34 "Main roof material: Ceramic tiles".
dichotomize (QH153=35) QH153_35 "Main roof material: Cement".
dichotomize (QH153=36) QH153_36 "Main roof material: Roofing shingles".
dichotomize (QH153=96) QH153_96 "Main roof material: Other".


* Main wall material.
dichotomize (QH154=11) QH154_11 "Main wall material: No walls".
dichotomize (QH154=12) QH154_12 "Main wall material: Cane/palm/trunks".
dichotomize (QH154=13) QH154_13 "Main wall material: Dirt".
dichotomize (QH154=21 | QH154=22) QH154_21 "Main wall material: Bamboo with mud/stone with mud".
*ichotomize (QH154=22) QH154_22 "Main wall material: Stone with mud".
dichotomize (QH154=23) QH154_23 "Main wall material: Uncovered adobe".
*ichotomize (QH154=24)  "Main wall material: Plywood".
dichotomize (QH154=25) QH154_25 "Main wall material: Cardboard".
dichotomize (QH154=26) QH154_26 "Main wall material: Reused wood".
dichotomize (QH154=31) QH154_31 "Main wall material: Cement".
dichotomize (QH154=32) QH154_32 "Main wall material: Stone with lime/cement".
dichotomize (QH154=33) QH154_33 "Main wall material: Bricks".
dichotomize (QH154=34) QH154_34 "Main wall material: Cement blocks".
dichotomize (QH154=36) QH154_36 "Main wall material: Wood planks/shingles".
dichotomize (QH154=37) QH154_37 "Main wall material: Tin".
dichotomize (QH154=96) QH154_96 "Main wall material: Other".


*{Members per sleeping room}.
if (hhusual=0) hhusual=hhslept.
if (QH127>0) memsleep=trunc(hhusual/QH127).
if (QH127=0) memsleep=hhusual.
if (missing(QH127) or QH127>=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 land.

* Toilet facility by shared/not shared.
crosstabs /tables=QH109 by QH110.

* Land area by units - if there are separate units - need to convert them to one unit.
*crosstabs /tables=QH131N by QH131U.

*drop QH109_31 QH109_31_sh QH129E_2 QH129_E3 QH153_13 QH153_24 QH154_22 .

frequencies variables=
  QH101_11 QH101_12 QH101_13 QH101_14 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42 QH101_51 QH101_61 QH101_71 QH101_81 QH101_91 QH101_96
  QH109_11 QH109_12 QH109_13 QH109_14 QH109_15 QH109_21 QH109_22 QH109_23  QH109_41 QH109_51 QH109_61 QH109_96
  QH109_11_sh QH109_12_sh QH109_13_sh QH109_14_sh QH109_15_sh QH109_21_sh QH109_22_sh QH109_23_sh  QH109_41_sh QH109_51_sh QH109_96_sh
  QH132A QH132B QH132C QH132D QH132E QH132F QH132G QH132H QH132I QH132J QH132K QH132L QH132M QH132N QH133A QH133B QH133C QH133D QH133E QH133F QH133G MOBPHONE
  CHECKACC QH152_11 QH152_12 QH152_21 QH152_22 QH152_31 QH152_32 QH152_33 QH152_34 QH152_35 QH152_96
  QH153_11 QH153_12  QH153_21 QH153_22 QH153_23  QH153_31 QH153_32 QH153_33 QH153_34 QH153_35 QH153_36 QH153_96
  QH154_11 QH154_12 QH154_13 QH154_21  QH154_23  QH154_25 QH154_26 QH154_31 QH154_32 QH154_33 QH154_34 QH154_36 QH154_37 QH154_96
  HOUSE LAND memsleep
  QH129A_1 QH129A_2 QH129A_3 QH129B_1 QH129B_2 QH129B_3
  QH129C_1 QH129C_2 QH129C_3 QH129D_1 QH129D_2 QH129D_3
  QH129E_1   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.

factor /variables
  QH101_11 QH101_12 QH101_13 QH101_14 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42 QH101_51 QH101_61 QH101_71 QH101_81 QH101_91 QH101_96
  QH109_11 QH109_12 QH109_13 QH109_14 QH109_15 QH109_21 QH109_22 QH109_23  QH109_41 QH109_51 QH109_61 QH109_96
  QH109_11_sh QH109_12_sh QH109_13_sh QH109_14_sh QH109_15_sh QH109_21_sh QH109_22_sh QH109_23_sh  QH109_41_sh QH109_51_sh QH109_96_sh
  QH132A QH132B QH132C QH132D QH132E QH132F QH132G QH132I QH132J QH132K QH132L QH132M QH132N QH133A QH133B QH133C QH133D QH133E QH133F QH133G MOBPHONE
  CHECKACC QH152_11 QH152_12 QH152_21 QH152_22 QH152_31 QH152_32 QH152_33 QH152_34 QH152_35 QH152_96
  QH153_11 QH153_12  QH153_21 QH153_22 QH153_23  QH153_31 QH153_32 QH153_33 QH153_34 QH153_35 QH153_36 QH153_96
  QH154_11 QH154_12 QH154_13 QH154_21  QH154_23  QH154_25 QH154_26 QH154_31 QH154_32 QH154_33 QH154_34 QH154_36 QH154_37 QH154_96
  HOUSE LAND memsleep
  QH129A_1 QH129A_2 QH129A_3 QH129B_1 QH129B_2 QH129B_3
  QH129C_1 QH129C_2 QH129C_3 QH129D_1 QH129D_2 QH129D_3
  QH129E_1   landarea
  /missing meansub
  /analysis
  QH101_11 QH101_12 QH101_13 QH101_14 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42 QH101_51 QH101_61 QH101_71 QH101_81 QH101_91 QH101_96
  QH109_11 QH109_12 QH109_13 QH109_14 QH109_15 QH109_21 QH109_22 QH109_23  QH109_41 QH109_51 QH109_61 QH109_96
  QH109_11_sh QH109_12_sh QH109_13_sh QH109_14_sh QH109_15_sh QH109_21_sh QH109_22_sh QH109_23_sh  QH109_41_sh QH109_51_sh QH109_96_sh
  QH132A QH132B QH132C QH132D QH132E QH132F QH132G QH132I QH132J QH132K QH132L QH132M QH132N QH133A QH133B QH133C QH133D QH133E QH133F QH133G MOBPHONE
  CHECKACC QH152_11 QH152_12 QH152_21 QH152_22 QH152_31 QH152_32 QH152_33 QH152_34 QH152_35 QH152_96
  QH153_11 QH153_12  QH153_21 QH153_22 QH153_23  QH153_31 QH153_32 QH153_33 QH153_34 QH153_35 QH153_36 QH153_96
  QH154_11 QH154_12 QH154_13 QH154_21  QH154_23  QH154_25 QH154_26 QH154_31 QH154_32 QH154_33 QH154_34 QH154_36 QH154_37 QH154_96
  HOUSE LAND memsleep
  QH129A_1 QH129A_2 QH129A_3 QH129B_1 QH129B_2 QH129B_3
  QH129C_1 QH129C_2 QH129C_3 QH129D_1 QH129D_2 QH129D_3
  QH129E_1   landarea
  /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

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

factor /variables
  QH101_11 QH101_12 QH101_13 QH101_14 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42 QH101_51 QH101_61 QH101_71 QH101_81 QH101_91 QH101_96
  QH109_11 QH109_12 QH109_13 QH109_14 QH109_15 QH109_21 QH109_22 QH109_23  QH109_41 QH109_51 QH109_61 QH109_96
  QH109_11_sh QH109_12_sh QH109_13_sh QH109_14_sh QH109_15_sh QH109_21_sh QH109_22_sh QH109_23_sh  QH109_41_sh QH109_51_sh QH109_96_sh
  QH132A QH132B QH132C QH132D QH132E QH132F QH132G QH132I QH132J QH132K QH132L QH132M QH132N QH133A QH133B QH133C QH133D QH133E QH133F QH133G MOBPHONE
  CHECKACC QH152_11 QH152_12 QH152_21 QH152_22 QH152_31 QH152_32 QH152_33 QH152_34 QH152_35 QH152_96
  QH153_11 QH153_12  QH153_21 QH153_22 QH153_23  QH153_31 QH153_32 QH153_33 QH153_34 QH153_35 QH153_36 QH153_96
  QH154_11 QH154_12 QH154_13 QH154_21  QH154_23  QH154_25 QH154_26 QH154_31 QH154_32 QH154_33 QH154_34 QH154_36 QH154_37 QH154_96
  HOUSE LAND memsleep
  /missing meansub
  /analysis
  QH101_11 QH101_12 QH101_13 QH101_14 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42 QH101_51 QH101_61 QH101_71 QH101_81 QH101_91 QH101_96
  QH109_11 QH109_12 QH109_13 QH109_14 QH109_15 QH109_21 QH109_22 QH109_23  QH109_41 QH109_51 QH109_61 QH109_96
  QH109_11_sh QH109_12_sh QH109_13_sh QH109_14_sh QH109_15_sh QH109_21_sh QH109_22_sh QH109_23_sh  QH109_41_sh QH109_51_sh QH109_96_sh
  QH132A QH132B QH132C QH132D QH132E QH132F QH132G QH132I QH132J QH132K QH132L QH132M QH132N QH133A QH133B QH133C QH133D QH133E QH133F QH133G MOBPHONE
  CHECKACC QH152_11 QH152_12 QH152_21 QH152_22 QH152_31 QH152_32 QH152_33 QH152_34 QH152_35 QH152_96
  QH153_11 QH153_12  QH153_21 QH153_22 QH153_23  QH153_31 QH153_32 QH153_33 QH153_34 QH153_35 QH153_36 QH153_96
  QH154_11 QH154_12 QH154_13 QH154_21  QH154_23  QH154_25 QH154_26 QH154_31 QH154_32 QH154_33 QH154_34 QH154_36 QH154_37 QH154_96
  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.

*Drop QH101_32 QH101_42 QH109_96 QH109_41_sh QH152_22 QH153_11 .
factor /variables
  QH101_11 QH101_12 QH101_13 QH101_14 QH101_21 QH101_31  QH101_41  QH101_51 QH101_61 QH101_71 QH101_81 QH101_91 QH101_96
  QH109_11 QH109_12 QH109_13 QH109_14 QH109_15 QH109_21 QH109_22 QH109_23  QH109_41 QH109_51 QH109_61 
  QH109_11_sh QH109_12_sh QH109_13_sh QH109_14_sh QH109_15_sh QH109_21_sh QH109_22_sh QH109_23_sh   QH109_51_sh QH109_96_sh
  QH132A QH132B QH132C QH132D QH132E QH132F QH132G QH132I QH132J QH132K QH132L QH132M QH132N QH133A QH133B QH133C QH133D QH133E QH133F QH133G MOBPHONE
  CHECKACC QH152_11 QH152_12 QH152_21  QH152_31 QH152_32 QH152_33 QH152_34 QH152_35 QH152_96
   QH153_12  QH153_21 QH153_22 QH153_23  QH153_31 QH153_32 QH153_33 QH153_34 QH153_35 QH153_36 QH153_96
  QH154_11 QH154_12 QH154_13 QH154_21  QH154_23  QH154_25 QH154_26 QH154_31 QH154_32 QH154_33 QH154_34 QH154_36 QH154_37 QH154_96
  HOUSE LAND memsleep
  /missing meansub
  /analysis
  QH101_11 QH101_12 QH101_13 QH101_14 QH101_21 QH101_31  QH101_41  QH101_51 QH101_61 QH101_71 QH101_81 QH101_91 QH101_96
  QH109_11 QH109_12 QH109_13 QH109_14 QH109_15 QH109_21 QH109_22 QH109_23  QH109_41 QH109_51 QH109_61 
  QH109_11_sh QH109_12_sh QH109_13_sh QH109_14_sh QH109_15_sh QH109_21_sh QH109_22_sh QH109_23_sh   QH109_51_sh QH109_96_sh
  QH132A QH132B QH132C QH132D QH132E QH132F QH132G QH132I QH132J QH132K QH132L QH132M QH132N QH133A QH133B QH133C QH133D QH133E QH133F QH133G MOBPHONE
  CHECKACC QH152_11 QH152_12 QH152_21  QH152_31 QH152_32 QH152_33 QH152_34 QH152_35 QH152_96
   QH153_12  QH153_21 QH153_22 QH153_23  QH153_31 QH153_32 QH153_33 QH153_34 QH153_35 QH153_36 QH153_96
  QH154_11 QH154_12 QH154_13 QH154_21  QH154_23  QH154_25 QH154_26 QH154_31 QH154_32 QH154_33 QH154_34 QH154_36 QH154_37 QH154_96
  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.

factor /variables
  QH101_11 QH101_12 QH101_13 QH101_14 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42 QH101_51 QH101_61 QH101_71 QH101_81 QH101_91 QH101_96
  QH109_11 QH109_12 QH109_13 QH109_14 QH109_15 QH109_21 QH109_22 QH109_23  QH109_41 QH109_51 QH109_61 QH109_96
  QH109_11_sh QH109_12_sh QH109_13_sh QH109_14_sh QH109_15_sh QH109_21_sh QH109_22_sh QH109_23_sh  QH109_41_sh QH109_51_sh QH109_96_sh
  QH132A QH132B QH132C QH132D QH132E QH132F QH132G QH132I QH132J QH132K QH132L QH132M QH132N QH133A QH133B QH133C QH133D QH133E QH133F QH133G MOBPHONE
  CHECKACC QH152_11 QH152_12 QH152_21 QH152_22 QH152_31 QH152_32 QH152_33 QH152_34 QH152_35 QH152_96
  QH153_11 QH153_12  QH153_21 QH153_22 QH153_23  QH153_31 QH153_32 QH153_33 QH153_34 QH153_35 QH153_36 QH153_96
  QH154_11 QH154_12 QH154_13 QH154_21  QH154_23  QH154_25 QH154_26 QH154_31 QH154_32 QH154_33 QH154_34 QH154_36 QH154_37 QH154_96
  HOUSE LAND memsleep
  QH129A_1 QH129A_2 QH129A_3 QH129B_1 QH129B_2 QH129B_3
  QH129C_1 QH129C_2 QH129C_3 QH129D_1 QH129D_2 QH129D_3
  QH129E_1   landarea
  /missing meansub
  /analysis
  QH101_11 QH101_12 QH101_13 QH101_14 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42 QH101_51 QH101_61 QH101_71 QH101_81 QH101_91 QH101_96
  QH109_11 QH109_12 QH109_13 QH109_14 QH109_15 QH109_21 QH109_22 QH109_23  QH109_41 QH109_51 QH109_61 QH109_96
  QH109_11_sh QH109_12_sh QH109_13_sh QH109_14_sh QH109_15_sh QH109_21_sh QH109_22_sh QH109_23_sh  QH109_41_sh QH109_51_sh QH109_96_sh
  QH132A QH132B QH132C QH132D QH132E QH132F QH132G QH132I QH132J QH132K QH132L QH132M QH132N QH133A QH133B QH133C QH133D QH133E QH133F QH133G MOBPHONE
  CHECKACC QH152_11 QH152_12 QH152_21 QH152_22 QH152_31 QH152_32 QH152_33 QH152_34 QH152_35 QH152_96
  QH153_11 QH153_12  QH153_21 QH153_22 QH153_23  QH153_31 QH153_32 QH153_33 QH153_34 QH153_35 QH153_36 QH153_96
  QH154_11 QH154_12 QH154_13 QH154_21  QH154_23  QH154_25 QH154_26 QH154_31 QH154_32 QH154_33 QH154_34 QH154_36 QH154_37 QH154_96
  HOUSE LAND memsleep
  QH129A_1 QH129A_2 QH129A_3 QH129B_1 QH129B_2 QH129B_3
  QH129C_1 QH129C_2 QH129C_3 QH129D_1 QH129D_2 QH129D_3
  QH129E_1   landarea
  /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.


compute hhwt = QHWEIGHT/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.
compute hhmemwt=QHWEIGHT*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.

filter off.
filter by rural.
execute.

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

filter off.
execute.

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

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

*** Check on quintiles.
frequencies variables=ncombsco nurbscor nrurscor.


weight by hhwt.

ctables /table (
  QH101_11+QH101_12+QH101_13+QH101_14+QH101_21+QH101_31+QH101_32+QH101_41+QH101_42+QH101_51+QH101_61+QH101_71+QH101_81+QH101_91+QH101_96+
  QH109_11+QH109_12+QH109_13+QH109_14+QH109_15+QH109_21+QH109_22+QH109_23+QH109_41+QH109_51+QH109_61+QH109_96+
  QH109_11_sh+QH109_12_sh+QH109_13_sh+QH109_14_sh+QH109_15_sh+QH109_21_sh+QH109_22_sh+QH109_23_sh+QH109_41_sh+QH109_51_sh+QH109_96_sh+
  QH132A+QH132B+QH132C+QH132D+QH132E+QH132F+QH132G+QH132I+QH132J+QH132K+QH132L+QH132M+QH132N+QH133A+QH133B+QH133C+QH133D+QH133E+QH133F+QH133G+MOBPHONE+
  CHECKACC+QH152_11+QH152_12+QH152_21+QH152_22+QH152_31+QH152_32+QH152_33+QH152_34+QH152_35+QH152_96+
  QH153_11+QH153_12+QH153_21+QH153_22+QH153_23+QH153_31+QH153_32+QH153_33+QH153_34+QH153_35+QH153_36+QH153_96+
  QH154_11+QH154_12+QH154_13+QH154_21+QH154_23+QH154_25+QH154_26+QH154_31+QH154_32+QH154_33+QH154_34+QH154_36+QH154_37+QH154_96+
  HOUSE+LAND+memsleep+
  QH129A_1+QH129A_2+QH129A_3+QH129B_1+QH129B_2+QH129B_3+
  QH129C_1+QH129C_2+QH129C_3+QH129D_1+QH129D_2+QH129D_3+
  QH129E_1+landarea 
  )[S][Mean F8.3] by (ncombsco+nurbscor+nrurscor)[C]
  /slabels visible=no.

* Alternative instead of ctables.
*means tables=
  QH101_11 QH101_12 QH101_13 QH101_14 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42 QH101_51 QH101_61 QH101_71 QH101_81 QH101_91 QH101_96
  QH109_11 QH109_12 QH109_13 QH109_14 QH109_15 QH109_21 QH109_22 QH109_23  QH109_41 QH109_51 QH109_61 QH109_96
  QH109_11_sh QH109_12_sh QH109_13_sh QH109_14_sh QH109_15_sh QH109_21_sh QH109_22_sh QH109_23_sh  QH109_41_sh QH109_51_sh QH109_96_sh
  QH132A QH132B QH132C QH132D QH132E QH132F QH132G QH132I QH132J QH132K QH132L QH132M QH132N QH133A QH133B QH133C QH133D QH133E QH133F QH133G MOBPHONE
  CHECKACC QH152_11 QH152_12 QH152_21 QH152_22 QH152_31 QH152_32 QH152_33 QH152_34 QH152_35 QH152_96
  QH153_11 QH153_12  QH153_21 QH153_22 QH153_23  QH153_31 QH153_32 QH153_33 QH153_34 QH153_35 QH153_36 QH153_96
  QH154_11 QH154_12 QH154_13 QH154_21  QH154_23  QH154_25 QH154_26 QH154_31 QH154_32 QH154_33 QH154_34 QH154_36 QH154_37 QH154_96
  HOUSE LAND memsleep
  QH129A_1 QH129A_2 QH129A_3 QH129B_1 QH129B_2 QH129B_3
  QH129C_1 QH129C_2 QH129C_3 QH129D_1 QH129D_2 QH129D_3
  QH129E_1   landarea
    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 /QHCLUST QHNUMBER combscor ncombsco urbscore nurbscor rurscore nrurscor.
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=QHTYPE QHDIVISION total Ncombsco display=both
  /table QHTYPE [C] + QHDIVISION [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, Bangladesh DHS 2022'
  corner='Residence/region' /slabels visible=no.