* Wealth index calculation. Trevor Croft, 06/05/2018. Albania DHS 2017.
cd 'C:\Users\21180\OneDrive - ICF\Projects\Analysis\Wealth Index Construction\AL71\wealth'.
include file='wealth_assets.sps'.
missing values QH123N (999999).
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 (QH109=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: 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=61) QH101_61 "Source of drinking water: Tanker truck".
dichotomize (QH101=71) QH101_71 "Source of drinking water: Cart with small tank".
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 (QH108=11) QH108_11 "Type of toilet facility: Flush to piped sewer system".
dichotomize (QH108=12) QH108_12 "Type of toilet facility: Flush to septic tank".
dichotomize (QH108=13) QH108_13 "Type of toilet facility: Flush to pit latrine".
dichotomize (QH108=14) QH108_14 "Type of toilet facility: Flush to somewhere else".
dichotomize (QH108=15) QH108_15 "Type of toilet facility: Flush, don't know where".
dichotomize (QH108=21) QH108_21 "Type of toilet facility: Ventilated improved pit latrine".
dichotomize (QH108=22) QH108_22 "Type of toilet facility: Pit latrine with slab".
dichotomize (QH108=23) QH108_23 "Type of toilet facility: Pit latrine without slab/open pit".
dichotomize (QH108=31) QH108_31 "Type of toilet facility: Composting toilet".
dichotomize (QH108=41) QH108_41 "Type of toilet facility: Bucket toilet".
dichotomize (QH108=51) QH108_51 "Type of toilet facility: Hanging toilet/hanging latrine".
dichotomize (QH108=61) QH108_61 "Type of toilet facility: No facility/bush/field".
dichotomize (QH108=96) QH108_96 "Type of toilet facility: Other".

shared_fac QH108_11 QH108_11_sh "Type of toilet facility: Flush to piped sewer system - shared".
shared_fac QH108_12 QH108_12_sh "Type of toilet facility: Flush to septic tank - shared".
shared_fac QH108_13 QH108_13_sh "Type of toilet facility: Flush to pit latrine - shared".
*hared_fac QH108_14 QH108_14_sh "Type of toilet facility: Flush to somewhere else - shared".
*hared_fac QH108_15 QH108_15_sh "Type of toilet facility: Flush, don't know where - shared".
*hared_fac QH108_21 QH108_21_sh "Type of toilet facility: Ventilated improved pit latrine - shared".
*hared_fac QH108_22 QH108_22_sh "Type of toilet facility: Pit latrine with slab - shared".
*hared_fac QH108_23 QH108_23_sh "Type of toilet facility: Pit latrine without slab/open pit - shared".
*hared_fac QH108_31 QH108_31_sh "Type of toilet facility: Composting toilet - shared".
*hared_fac QH108_41 QH108_41_sh "Type of toilet facility: Bucket toilet - shared".
*hared_fac QH108_51 QH108_51_sh "Type of toilet facility: Hanging toilet/hanging latrine - shared".
*hared_fac QH108_96 QH108_96_sh "Type of toilet facility: Other - shared".

* Radio.
no2zero QH111A.
* Television.
no2zero QH111B.
* Mobile telephone.
no2zero QH111C.
* Telephone (non-mobile).
no2zero QH111D.
* Video player or DVD player.
no2zero QH111E.
* Tape player or CD player.
no2zero QH111F.
* Refrigerator.
no2zero QH111G.
* Freezer.
no2zero QH111H.
* Washing machine.
no2zero QH111I.
* Dishwasher.
no2zero QH111J.
* Microwave.
no2zero QH111K.
* Sofa.
no2zero QH111L.
* Armoire.
no2zero QH111M.
* Electric radiator.
no2zero QH111N.
* Generator.
no2zero QH111O.
* Sewing/knitting machine.
no2zero QH111P.
* Air conditioner.
no2zero QH111Q.
* Water boiler.
no2zero QH111R.
* Computer.
no2zero QH111S.
* Satellite dish or cable receiver.
no2zero QH111T.

* Type of cooking fuel.
dichotomize (QH112=1) QH112_1 "Type of cooking fuel: Electricity".
dichotomize (QH112=2) QH112_2 "Type of cooking fuel: LPG".
dichotomize (QH112=3) QH112_3 "Type of cooking fuel: Natural gas".
dichotomize (QH112=5) QH112_5 "Type of cooking fuel: Kerosene".
*ichotomize (QH112=6) QH112_6 "Type of cooking fuel: Coal, lignite".
dichotomize (QH112=6 or QH112=7) QH112_7 "Type of cooking fuel: Coal, lignite or Charcoal".
dichotomize (QH112=8) QH112_8 "Type of cooking fuel: Wood".
dichotomize (QH112=10) QH112_10 "Type of cooking fuel: Agricultural crop".
dichotomize (QH112=95) QH112_95 "Type of cooking fuel: No food cooked in household".
dichotomize (QH112=96) QH112_96 "Type of cooking fuel: Other".


* Main floor material.
dichotomize (QH117=11) QH117_11 "Main floor material: Earth/sand".
dichotomize (QH117=21) QH117_21 "Main floor material: Wood planks".
dichotomize (QH117=31) QH117_31 "Main floor material: Parquet or polished wood".
dichotomize (QH117=32) QH117_32 "Main floor material: Vinyl or asphalt strips".
dichotomize (QH117=33) QH117_33 "Main floor material: Ceramic tiles".
dichotomize (QH117=34) QH117_34 "Main floor material: Cement".
dichotomize (QH117=35) QH117_35 "Main floor material: Carpet".
dichotomize (QH117=96) QH117_96 "Main floor material: Other".


* Main roof material.
dichotomize (QH118=21) QH118_21 "Main roof material: Rustic mat".
dichotomize (QH118=23) QH118_23 "Main roof material: Wood planks".
dichotomize (QH118=24) QH118_24 "Main roof material: Cardboard".
dichotomize (QH118=31) QH118_31 "Main roof material: Metal".
dichotomize (QH118=32) QH118_32 "Main roof material: Wood".
dichotomize (QH118=33) QH118_33 "Main roof material: Calamine/cement fiber".
dichotomize (QH118=34) QH118_34 "Main roof material: Ceramic tiles".
dichotomize (QH118=35) QH118_35 "Main roof material: Cement".
dichotomize (QH118=36) QH118_36 "Main roof material: Roofing shingles".
dichotomize (QH118=37) QH118_37 "Main roof material: Reinforced concrete".
dichotomize (QH118=96) QH118_96 "Main roof material: Other".


* Main wall material.
dichotomize (QH119=22) QH119_22 "Main wall material: Stone with mud".
dichotomize (QH119=23) QH119_23 "Main wall material: Uncovered adobe".
*ichotomize (QH119=24) QH119_24 "Main wall material: Plywood".
dichotomize (QH119=25) QH119_25 "Main wall material: Cardboard".
dichotomize (QH119=24 or QH119=26) QH119_26 "Main wall material: Reused wood or Plywood".
dichotomize (QH119=31) QH119_31 "Main wall material: Cement".
dichotomize (QH119=32) QH119_32 "Main wall material: Stone with lime/cement".
dichotomize (QH119=33) QH119_33 "Main wall material: Bricks".
dichotomize (QH119=34) QH119_34 "Main wall material: Cement blocks".
dichotomize (QH119=35) QH119_35 "Main wall material: Covered adobe".
dichotomize (QH119=36) QH119_36 "Main wall material: Wood planks/shingles".
dichotomize (QH119=96) QH119_96 "Main wall material: Other".

* Watch.
no2zero QH121A.
* Bicycle.
no2zero QH121B.
* Motorcycle or scooter.
no2zero QH121C.
* Animal-drawn cart.
no2zero QH121D.
* Car or Truck.
no2zero QH121E.
* Tractor.
no2zero QH121F.
* Boat with a motor.
no2zero QH121G.

* Agricultural land (number).
compute landarea = 0.
if (QH123U = 1) landarea = QH123N*10000. /* Hectare = 10000 sq. meters */
if (QH123U = 2) landarea = QH123N* 1000. /* Dynym   =  1000 sq. meters */
if (QH123U = 3) landarea = QH123N.       /* sq. meters */
if (QH123N = 999995) landarea = 950000.
if (landarea > 950000) landarea = 950000.
if (QH123U >= 8) landarea = 0.
if (missing(QH123N) | QH123N >= 999998) landarea=999999.
if (missing(QH122 ) | QH122 <> 1) landarea=0.
missing values landarea (999999).

* Cattle.
if (missing(QH125A) | QH124 <> 1) QH125A=0.
missing values QH125A (99).
compute QH125A_1 = (QH125A >= 1 & QH125A <= 4).
compute QH125A_2 = (QH125A >= 5 & QH125A <= 9).
compute QH125A_3 = (QH125A >= 10 & QH125A <= 98).
variable labels QH125A_1 'Cattle: 1-4' /QH125A_2 'Cattle: 5-9' /QH125A_3 'Cattle: 10+'.


* Cows/bulls.
if (missing(QH125B) | QH124 <> 1) QH125B=0.
missing values QH125B (99).
compute QH125B_1 = (QH125B >= 1 & QH125B <= 4).
compute QH125B_2 = (QH125B >= 5 & QH125B <= 9).
compute QH125B_3 = (QH125B >= 10 & QH125B <= 98).
variable labels QH125B_1 'Cows/bulls: 1-4' /QH125B_2 'Cows/bulls: 5-9' /QH125B_3 'Cows/bulls: 10+'.


* Horses/donkeys/mules.
if (missing(QH125C) | QH124 <> 1) QH125C=0.
missing values QH125C (99).
compute QH125C_1 = (QH125C >= 1 & QH125C <= 4).
compute QH125C_2 = (QH125C >= 5 & QH125C <= 9).
compute QH125C_3 = (QH125C >= 10 & QH125C <= 98).
variable labels QH125C_1 'Horses/donkeys/mules: 1-4' /QH125C_2 'Horses/donkeys/mules: 5-9' /QH125C_3 'Horses/donkeys/mules: 10+'.


* Goats.
if (missing(QH125D) | QH124 <> 1) QH125D=0.
missing values QH125D (99).
compute QH125D_1 = (QH125D >= 1 & QH125D <= 4).
compute QH125D_2 = (QH125D >= 5 & QH125D <= 9).
compute QH125D_3 = (QH125D >= 10 & QH125D <= 98).
variable labels QH125D_1 'Goats: 1-4' /QH125D_2 'Goats: 5-9' /QH125D_3 'Goats: 10+'.


* Sheep.
if (missing(QH125E) | QH124 <> 1) QH125E=0.
missing values QH125E (99).
compute QH125E_1 = (QH125E >= 1 & QH125E <= 4).
compute QH125E_2 = (QH125E >= 5 & QH125E <= 9).
compute QH125E_3 = (QH125E >= 10 & QH125E <= 98).
variable labels QH125E_1 'Sheep: 1-4' /QH125E_2 'Sheep: 5-9' /QH125E_3 'Sheep: 10+'.


* Chickens or other poultry.
if (missing(QH125F) | QH124 <> 1) QH125F=0.
missing values QH125F (99).
compute QH125F_1 = (QH125F >= 1 & QH125F <= 9).
compute QH125F_2 = (QH125F >= 10 & QH125F <= 29).
compute QH125F_3 = (QH125F >= 30 & QH125F <= 98).
variable labels QH125F_1 'Chickens or other poultry: 1-9' /QH125F_2 'Chickens or other poultry: 10-29' /QH125F_3 'Chickens or other poultry: 30+'.


* Pigs.
if (missing(QH125G) | QH124 <> 1) QH125G=0.
missing values QH125G (99).
compute QH125G_1 = (QH125G >= 1 & QH125G <= 4).
compute QH125G_2 = (QH125G >= 5 & QH125G <= 9).
compute QH125G_3 = (QH125G >= 10 & QH125G <= 98).
variable labels QH125G_1 'Pigs: 1-4' /QH125G_2 'Pigs: 5-9' /QH125G_3 'Pigs: 10+'.

* Bank account.
no2zero QH126.
*{Members per sleeping room}.
if (hhusual=0) hhusual=hhslept.
if (QH120>0) memsleep=trunc(hhusual/QH120).
if (QH120=0) memsleep=hhusual.
if (missing(QH120) or QH120>=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=QH108 by QH109.

* Land area by units - if there are separate units - need to convert them to one unit.
crosstabs /tables=QH123N by QH123U.

* Dropped QH108_14_sh to QH108_96_sh, QH112_6, QH119_24 .
frequencies variables=
  QH101_11 QH101_12 QH101_13 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42 QH101_61 QH101_71 QH101_91 QH101_96
  QH108_11 QH108_12 QH108_13 QH108_14 QH108_15 QH108_21 QH108_22 QH108_23 QH108_31 QH108_41 QH108_51 QH108_61 QH108_96
  QH108_11_sh QH108_12_sh QH108_13_sh
  QH111A QH111B QH111C QH111D QH111E QH111F QH111G QH111H QH111I QH111J QH111K QH111L QH111M QH111N QH111O QH111P QH111Q QH111R QH111S QH111T
  QH112_1 QH112_2 QH112_3 QH112_5  QH112_7 QH112_8 QH112_10 QH112_95 QH112_96
  QH117_11 QH117_21 QH117_31 QH117_32 QH117_33 QH117_34 QH117_35 QH117_96
  QH118_21 QH118_23 QH118_24 QH118_31 QH118_32 QH118_33 QH118_34 QH118_35 QH118_36 QH118_37 QH118_96
  QH119_22 QH119_23 QH119_25 QH119_26 QH119_31 QH119_32 QH119_33 QH119_34 QH119_35 QH119_36 QH119_96
  QH121A QH121B QH121C QH121D QH121E QH121F QH121G QH126 DOMESTIC HOUSE LAND memsleep
  landarea QH125A_1 QH125A_2 QH125A_3 QH125B_1 QH125B_2 QH125B_3
  QH125C_1 QH125C_2 QH125C_3 QH125D_1 QH125D_2 QH125D_3
  QH125E_1 QH125E_2 QH125E_3 QH125F_1 QH125F_2 QH125F_3
  QH125G_1 QH125G_2 QH125G_3
.

* 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.

* Dropped QH108_41 QH108_14_sh to QH108_96_sh, QH112_6, QH119_24 .
factor /variables
  QH101_11 QH101_12 QH101_13 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42 QH101_61 QH101_71 QH101_91 QH101_96
  QH108_11 QH108_12 QH108_13 QH108_14 QH108_15 QH108_21 QH108_22 QH108_23 QH108_31 QH108_51 QH108_61 QH108_96
  QH108_11_sh QH108_12_sh QH108_13_sh
  QH111A QH111B QH111C QH111D QH111E QH111F QH111G QH111H QH111I QH111J QH111K QH111L QH111M QH111N QH111O QH111P QH111Q QH111R QH111S QH111T
  QH112_1 QH112_2 QH112_3 QH112_5 QH112_7 QH112_8 QH112_10 QH112_95 QH112_96
  QH117_11 QH117_21 QH117_31 QH117_32 QH117_33 QH117_34 QH117_35 QH117_96
  QH118_21 QH118_23 QH118_24 QH118_31 QH118_32 QH118_33 QH118_34 QH118_35 QH118_36 QH118_37 QH118_96
  QH119_22 QH119_23 QH119_25 QH119_26 QH119_31 QH119_32 QH119_33 QH119_34 QH119_35 QH119_36 QH119_96
  QH121A QH121B QH121C QH121D QH121E QH121F QH121G QH126 HOUSE LAND memsleep
  landarea QH125A_1 QH125A_2 QH125A_3 QH125B_1 QH125B_2 QH125B_3
  QH125C_1 QH125C_2 QH125C_3 QH125D_1 QH125D_2 QH125D_3
  QH125E_1 QH125E_2 QH125E_3 QH125F_1 QH125F_2 QH125F_3
  QH125G_1 QH125G_2 QH125G_3
  /missing meansub
  /analysis
  QH101_11 QH101_12 QH101_13 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42 QH101_61 QH101_71 QH101_91 QH101_96
  QH108_11 QH108_12 QH108_13 QH108_14 QH108_15 QH108_21 QH108_22 QH108_23 QH108_31 QH108_51 QH108_61 QH108_96
  QH108_11_sh QH108_12_sh QH108_13_sh
  QH111A QH111B QH111C QH111D QH111E QH111F QH111G QH111H QH111I QH111J QH111K QH111L QH111M QH111N QH111O QH111P QH111Q QH111R QH111S QH111T
  QH112_1 QH112_2 QH112_3 QH112_5 QH112_7 QH112_8 QH112_10 QH112_95 QH112_96
  QH117_11 QH117_21 QH117_31 QH117_32 QH117_33 QH117_34 QH117_35 QH117_96
  QH118_21 QH118_23 QH118_24 QH118_31 QH118_32 QH118_33 QH118_34 QH118_35 QH118_36 QH118_37 QH118_96
  QH119_22 QH119_23 QH119_25 QH119_26 QH119_31 QH119_32 QH119_33 QH119_34 QH119_35 QH119_36 QH119_96
  QH121A QH121B QH121C QH121D QH121E QH121F QH121G QH126 HOUSE LAND memsleep
  landarea QH125A_1 QH125A_2 QH125A_3 QH125B_1 QH125B_2 QH125B_3
  QH125C_1 QH125C_2 QH125C_3 QH125D_1 QH125D_2 QH125D_3
  QH125E_1 QH125E_2 QH125E_3 QH125F_1 QH125F_2 QH125F_3
  QH125G_1 QH125G_2 QH125G_3
  /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.

factor /variables
  QH101_11 QH101_12 QH101_13 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42 QH101_61 QH101_71 QH101_91 QH101_96
  QH108_11 QH108_12 QH108_13 QH108_14 QH108_15 QH108_21 QH108_22 QH108_23 QH108_31 QH108_51 QH108_61 QH108_96
  QH108_11_sh QH108_12_sh QH108_13_sh
  QH111A QH111B QH111C QH111D QH111E QH111F QH111G QH111H QH111I QH111J QH111K QH111L QH111M QH111N QH111O QH111P QH111Q QH111R QH111S QH111T
  QH112_1 QH112_2 QH112_3 QH112_5 QH112_7 QH112_8 QH112_10 QH112_95 QH112_96
  QH117_11 QH117_21 QH117_31 QH117_32 QH117_33 QH117_34 QH117_35 QH117_96
  QH118_21 QH118_23 QH118_24 QH118_31 QH118_32 QH118_33 QH118_34 QH118_35 QH118_36 QH118_37 QH118_96
  QH119_22 QH119_23 QH119_25 QH119_26 QH119_31 QH119_32 QH119_33 QH119_34 QH119_35 QH119_36 QH119_96
  QH121A QH121B QH121C QH121D QH121E QH121F QH121G QH126 HOUSE LAND memsleep
  /missing meansub
  /analysis
  QH101_11 QH101_12 QH101_13 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42 QH101_61 QH101_71 QH101_91 QH101_96
  QH108_11 QH108_12 QH108_13 QH108_14 QH108_15 QH108_21 QH108_22 QH108_23 QH108_31 QH108_51 QH108_61 QH108_96
  QH108_11_sh QH108_12_sh QH108_13_sh
  QH111A QH111B QH111C QH111D QH111E QH111F QH111G QH111H QH111I QH111J QH111K QH111L QH111M QH111N QH111O QH111P QH111Q QH111R QH111S QH111T
  QH112_1 QH112_2 QH112_3 QH112_5 QH112_7 QH112_8 QH112_10 QH112_95 QH112_96
  QH117_11 QH117_21 QH117_31 QH117_32 QH117_33 QH117_34 QH117_35 QH117_96
  QH118_21 QH118_23 QH118_24 QH118_31 QH118_32 QH118_33 QH118_34 QH118_35 QH118_36 QH118_37 QH118_96
  QH119_22 QH119_23 QH119_25 QH119_26 QH119_31 QH119_32 QH119_33 QH119_34 QH119_35 QH119_36 QH119_96
  QH121A QH121B QH121C QH121D QH121E QH121F QH121G QH126 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.

* Dropped QH108_51 QH125B_2 QH125C_2 QH125C_3.
factor /variables
  QH101_11 QH101_12 QH101_13 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42 QH101_61 QH101_71 QH101_91 QH101_96
  QH108_11 QH108_12 QH108_13 QH108_14 QH108_15 QH108_21 QH108_22 QH108_23 QH108_31 QH108_61 QH108_96
  QH108_11_sh QH108_12_sh QH108_13_sh
  QH111A QH111B QH111C QH111D QH111E QH111F QH111G QH111H QH111I QH111J QH111K QH111L QH111M QH111N QH111O QH111P QH111Q QH111R QH111S QH111T
  QH112_1 QH112_2 QH112_3 QH112_5 QH112_7 QH112_8 QH112_10 QH112_95 QH112_96
  QH117_11 QH117_21 QH117_31 QH117_32 QH117_33 QH117_34 QH117_35 QH117_96
  QH118_21 QH118_23 QH118_24 QH118_31 QH118_32 QH118_33 QH118_34 QH118_35 QH118_36 QH118_37 QH118_96
  QH119_22 QH119_23 QH119_25 QH119_26 QH119_31 QH119_32 QH119_33 QH119_34 QH119_35 QH119_36 QH119_96
  QH121A QH121B QH121C QH121D QH121E QH121F QH121G QH126 HOUSE LAND memsleep
  landarea QH125A_1 QH125A_2 QH125A_3 QH125B_1 QH125B_3
  QH125C_1 QH125D_1 QH125D_2 QH125D_3
  QH125E_1 QH125E_2 QH125E_3 QH125F_1 QH125F_2 QH125F_3
  QH125G_1 QH125G_2 QH125G_3
  /missing meansub
  /analysis
  QH101_11 QH101_12 QH101_13 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42 QH101_61 QH101_71 QH101_91 QH101_96
  QH108_11 QH108_12 QH108_13 QH108_14 QH108_15 QH108_21 QH108_22 QH108_23 QH108_31 QH108_61 QH108_96
  QH108_11_sh QH108_12_sh QH108_13_sh
  QH111A QH111B QH111C QH111D QH111E QH111F QH111G QH111H QH111I QH111J QH111K QH111L QH111M QH111N QH111O QH111P QH111Q QH111R QH111S QH111T
  QH112_1 QH112_2 QH112_3 QH112_5 QH112_7 QH112_8 QH112_10 QH112_95 QH112_96
  QH117_11 QH117_21 QH117_31 QH117_32 QH117_33 QH117_34 QH117_35 QH117_96
  QH118_21 QH118_23 QH118_24 QH118_31 QH118_32 QH118_33 QH118_34 QH118_35 QH118_36 QH118_37 QH118_96
  QH119_22 QH119_23 QH119_25 QH119_26 QH119_31 QH119_32 QH119_33 QH119_34 QH119_35 QH119_36 QH119_96
  QH121A QH121B QH121C QH121D QH121E QH121F QH121G QH126 HOUSE LAND memsleep
  landarea QH125A_1 QH125A_2 QH125A_3 QH125B_1 QH125B_3
  QH125C_1 QH125D_1 QH125D_2 QH125D_3
  QH125E_1 QH125E_2 QH125E_3 QH125F_1 QH125F_2 QH125F_3
  QH125G_1 QH125G_2 QH125G_3
  /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_21 QH101_31 QH101_32 QH101_41 QH101_42 QH101_61 QH101_71 QH101_91 QH101_96
  QH108_11 QH108_12 QH108_13 QH108_14 QH108_15 QH108_21 QH108_22 QH108_23 QH108_31 QH108_51 QH108_61 QH108_96
  QH108_11_sh QH108_12_sh QH108_13_sh
  QH111A QH111B QH111C QH111D QH111E QH111F QH111G QH111H QH111I QH111J QH111K QH111L QH111M QH111N QH111O QH111P QH111Q QH111R QH111S QH111T
  QH112_1 QH112_2 QH112_3 QH112_5 QH112_7 QH112_8 QH112_10 QH112_95 QH112_96
  QH117_11 QH117_21 QH117_31 QH117_32 QH117_33 QH117_34 QH117_35 QH117_96
  QH118_21 QH118_23 QH118_24 QH118_31 QH118_32 QH118_33 QH118_34 QH118_35 QH118_36 QH118_37 QH118_96
  QH119_22 QH119_23 QH119_25 QH119_26 QH119_31 QH119_32 QH119_33 QH119_34 QH119_35 QH119_36 QH119_96
  QH121A QH121B QH121C QH121D QH121E QH121F QH121G QH126 HOUSE LAND memsleep
  landarea QH125A_1 QH125A_2 QH125A_3 QH125B_1 QH125B_2 QH125B_3
  QH125C_1 QH125C_2 QH125C_3 QH125D_1 QH125D_2 QH125D_3
  QH125E_1 QH125E_2 QH125E_3 QH125F_1 QH125F_2 QH125F_3
  QH125G_1 QH125G_2 QH125G_3
  /missing meansub
  /analysis
  QH101_11 QH101_12 QH101_13 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42 QH101_61 QH101_71 QH101_91 QH101_96
  QH108_11 QH108_12 QH108_13 QH108_14 QH108_15 QH108_21 QH108_22 QH108_23 QH108_31 QH108_51 QH108_61 QH108_96
  QH108_11_sh QH108_12_sh QH108_13_sh
  QH111A QH111B QH111C QH111D QH111E QH111F QH111G QH111H QH111I QH111J QH111K QH111L QH111M QH111N QH111O QH111P QH111Q QH111R QH111S QH111T
  QH112_1 QH112_2 QH112_3 QH112_5 QH112_7 QH112_8 QH112_10 QH112_95 QH112_96
  QH117_11 QH117_21 QH117_31 QH117_32 QH117_33 QH117_34 QH117_35 QH117_96
  QH118_21 QH118_23 QH118_24 QH118_31 QH118_32 QH118_33 QH118_34 QH118_35 QH118_36 QH118_37 QH118_96
  QH119_22 QH119_23 QH119_25 QH119_26 QH119_31 QH119_32 QH119_33 QH119_34 QH119_35 QH119_36 QH119_96
  QH121A QH121B QH121C QH121D QH121E QH121F QH121G QH126 HOUSE LAND memsleep
  landarea QH125A_1 QH125A_2 QH125A_3 QH125B_1 QH125B_2 QH125B_3
  QH125C_1 QH125C_2 QH125C_3 QH125D_1 QH125D_2 QH125D_3
  QH125E_1 QH125E_2 QH125E_3 QH125F_1 QH125F_2 QH125F_3
  QH125G_1 QH125G_2 QH125G_3
  /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_21+QH101_31+QH101_32+QH101_41+QH101_42+QH101_61+QH101_71+QH101_91+QH101_96+
  QH108_11+QH108_12+QH108_13+QH108_14+QH108_15+QH108_21+QH108_22+QH108_23+QH108_31+QH108_51+QH108_61+QH108_96+
  QH108_11_sh+QH108_12_sh+QH108_13_sh+
  QH111A+QH111B+QH111C+QH111D+QH111E+QH111F+QH111G+QH111H+QH111I+QH111J+QH111K+QH111L+QH111M+QH111N+QH111O+QH111P+QH111Q+QH111R+QH111S+QH111T+
  QH112_1+QH112_2+QH112_3+QH112_5+QH112_7+QH112_8+QH112_10+QH112_95+QH112_96+
  QH117_11+QH117_21+QH117_31+QH117_32+QH117_33+QH117_34+QH117_35+QH117_96+
  QH118_21+QH118_23+QH118_24+QH118_31+QH118_32+QH118_33+QH118_34+QH118_35+QH118_36+QH118_37+QH118_96+
  QH119_22+QH119_23+QH119_25+QH119_26+QH119_31+QH119_32+QH119_33+QH119_34+QH119_35+QH119_36+QH119_96+
  QH121A+QH121B+QH121C+QH121D+QH121E+QH121F+QH121G+QH126+HOUSE+LAND+memsleep+
  landarea+QH125A_1+QH125A_2+QH125A_3+QH125B_1+QH125B_2+QH125B_3+
  QH125C_1+QH125C_2+QH125C_3+QH125D_1+QH125D_2+QH125D_3+
  QH125E_1+QH125E_2+QH125E_3+QH125F_1+QH125F_2+QH125F_3+
  QH125G_1+QH125G_2+QH125G_3
  )[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_21 QH101_31 QH101_32 QH101_41 QH101_42 QH101_61 QH101_71 QH101_91 QH101_96
  QH108_11 QH108_12 QH108_13 QH108_14 QH108_15 QH108_21 QH108_22 QH108_23 QH108_31 QH108_51 QH108_61 QH108_96
  QH108_11_sh QH108_12_sh QH108_13_sh
  QH111A QH111B QH111C QH111D QH111E QH111F QH111G QH111H QH111I QH111J QH111K QH111L QH111M QH111N QH111O QH111P QH111Q QH111R QH111S QH111T
  QH112_1 QH112_2 QH112_3 QH112_5 QH112_7 QH112_8 QH112_10 QH112_95 QH112_96
  QH117_11 QH117_21 QH117_31 QH117_32 QH117_33 QH117_34 QH117_35 QH117_96
  QH118_21 QH118_23 QH118_24 QH118_31 QH118_32 QH118_33 QH118_34 QH118_35 QH118_36 QH118_37 QH118_96
  QH119_22 QH119_23 QH119_25 QH119_26 QH119_31 QH119_32 QH119_33 QH119_34 QH119_35 QH119_36 QH119_96
  QH121A QH121B QH121C QH121D QH121E QH121F QH121G QH126 HOUSE LAND memsleep
  landarea QH125A_1 QH125A_2 QH125A_3 QH125B_1 QH125B_2 QH125B_3
  QH125C_1 QH125C_2 QH125C_3 QH125D_1 QH125D_2 QH125D_3
  QH125E_1 QH125E_2 QH125E_3 QH125F_1 QH125F_2 QH125F_3
  QH125G_1 QH125G_2 QH125G_3
    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 QHREGION total Ncombsco display=both
  /table QHTYPE [C] + QHREGION [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, Albania DHS 2017   '
  corner='Residence/region' /slabels visible=no.