* Wealth index calculation. Trevor Croft, 01/02/2018. Tajikistan DHS 2017.

* The urban scores have been reversed from those initially produced as the PCA produced factor loadings that are reversed from usual direction,
* with assets usually associated with wealth initially receiving negative scores, assets associated with poorer households receiving positive scores.
* The reversal is achieved by the use of the following statement below:
* compute urbscore = 0 - urbscore.
* Factor loadings from the output file, though, will need to be negated to produce the final urban scores.

cd 'C:\Users\21180\OneDrive - ICF\Projects\Analysis\Wealth Index Construction\TJDHS2016\wealth_v2'.
include file='wealth_assets.sps'.
missing values QH120 (9999).
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".
*ichotomize (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".
*ichotomize (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".
dichotomize (QH109=31) QH109_31 "Type of toilet facility: Composting toilet".
dichotomize (QH109=41) QH109_41 "Type of toilet facility: Bucket toilet".
*ichotomize (QH109=51) QH109_51 "Type of toilet facility: Hanging toilet/hanging latrine".
*ichotomize (QH109=61) QH109_61 "Type of toilet facility: No facility/bush/field".
dichotomize (QH109=15 or QH109=51 or QH109=61 or 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".
*hared_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".
*hared_fac QH109_14 QH109_14_sh "Type of toilet facility: Flush to somewhere else - shared".
*hared_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".
*hared_fac QH109_41 QH109_41_sh "Type of toilet facility: Bucket toilet - shared".
*hared_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".


* Type of cooking fuel.
dichotomize (QH113=1) QH113_1 "Type of cooking fuel: Electricity".
dichotomize (QH113=2) QH113_2 "Type of cooking fuel: LPG".
dichotomize (QH113=3) QH113_3 "Type of cooking fuel: Natural gas".
dichotomize (QH113=4) QH113_4 "Type of cooking fuel: Biogas".
dichotomize (QH113=5) QH113_5 "Type of cooking fuel: Kerosene".
dichotomize (QH113=6) QH113_6 "Type of cooking fuel: Coal, lignite".
dichotomize (QH113=7) QH113_7 "Type of cooking fuel: Charcoal".
dichotomize (QH113=8) QH113_8 "Type of cooking fuel: Wood".
dichotomize (QH113=9) QH113_9 "Type of cooking fuel: Straw/shrubs/grass".
dichotomize (QH113=10) QH113_10 "Type of cooking fuel: Agricultural crop".
dichotomize (QH113=11) QH113_11 "Type of cooking fuel: Animal dung".
dichotomize (QH113=95) QH113_95 "Type of cooking fuel: No food cooked in household".
*ichotomize (QH113=96) QH113_96 "Type of cooking fuel: Other".


* Cows/bulls.
if (missing(QH118A) | QH117 <> 1) QH118A=0.
missing values QH118A (99).
compute QH118A_1 = (QH118A >= 1 & QH118A <= 4).
compute QH118A_2 = (QH118A >= 5 & QH118A <= 9).
compute QH118A_3 = (QH118A >= 10 & QH118A <= 98).
variable labels QH118A_1 'Cows/bulls: 1-4' /QH118A_2 'Cows/bulls: 5-9' /QH118A_3 'Cows/bulls: 10+'.


* Other cattle.
if (missing(QH118B) | QH117 <> 1) QH118B=0.
missing values QH118B (99).
compute QH118B_1 = (QH118B >= 1 & QH118B <= 4).
compute QH118B_2 = (QH118B >= 5 & QH118B <= 9).
compute QH118B_3 = (QH118B >= 10 & QH118B <= 98).
variable labels QH118B_1 'Other cattle: 1-4' /QH118B_2 'Other cattle: 5-9' /QH118B_3 'Other cattle: 10+'.


* Horses/donkeys/mules.
if (missing(QH118C) | QH117 <> 1) QH118C=0.
missing values QH118C (99).
compute QH118C_1 = (QH118C >= 1 & QH118C <= 4).
compute QH118C_2 = (QH118C >= 5 & QH118C <= 9).
compute QH118C_3 = (QH118C >= 10 & QH118C <= 98).
variable labels QH118C_1 'Horses/donkeys/mules: 1-4' /QH118C_2 'Horses/donkeys/mules: 5-9' /QH118C_3 'Horses/donkeys/mules: 10+'.


* Goats.
if (missing(QH118D) | QH117 <> 1) QH118D=0.
missing values QH118D (99).
compute QH118D_1 = (QH118D >= 1 & QH118D <= 4).
compute QH118D_2 = (QH118D >= 5 & QH118D <= 9).
compute QH118D_3 = (QH118D >= 10 & QH118D <= 98).
variable labels QH118D_1 'Goats: 1-4' /QH118D_2 'Goats: 5-9' /QH118D_3 'Goats: 10+'.


* Sheep.
if (missing(QH118E) | QH117 <> 1) QH118E=0.
missing values QH118E (99).
compute QH118E_1 = (QH118E >= 1 & QH118E <= 4).
compute QH118E_2 = (QH118E >= 5 & QH118E <= 9).
compute QH118E_3 = (QH118E >= 10 & QH118E <= 98).
variable labels QH118E_1 'Sheep: 1-4' /QH118E_2 'Sheep: 5-9' /QH118E_3 'Sheep: 10+'.


* Chickens or other poultry.
if (missing(QH118F) | QH117 <> 1) QH118F=0.
missing values QH118F (99).
compute QH118F_1 = (QH118F >= 1 & QH118F <= 9).
compute QH118F_2 = (QH118F >= 9 & QH118F <= 29).
compute QH118F_3 = (QH118F >= 30 & QH118F <= 98).
variable labels QH118F_1 'Chickens or other poultry: 1-9' /QH118F_2 'Chickens or other poultry: 10-29' /QH118F_3 'Chickens or other poultry: 30+'.


* Pigs.
if (missing(QH118G) | QH117 <> 1) QH118G=0.
missing values QH118G (99).
compute QH118G_1 = (QH118G >= 1 & QH118G <= 4).
compute QH118G_2 = (QH118G >= 5 & QH118G <= 9).
compute QH118G_3 = (QH118G >= 10 & QH118G <= 98).
variable labels QH118G_1 'Pigs: 1-4' /QH118G_2 'Pigs: 5-9' /QH118G_3 'Pigs: 10+'.


* Rabbits.
if (missing(QH118H) | QH117 <> 1) QH118H=0.
missing values QH118H (99).
compute QH118H_1 = (QH118H >= 1 & QH118H <= 4).
compute QH118H_2 = (QH118H >= 5 & QH118H <= 98).
*compute QH118H_3 = (QH118H >= 10 & QH118H <= 98).
variable labels QH118H_1 'Rabbits: 1-4' /QH118H_2 'Rabbits: 5+'.


* Fur animals.
if (missing(QH118I) | QH117 <> 1) QH118I=0.
missing values QH118I (99).
compute QH118I_1 = (QH118I >= 1 & QH118I <= 4).
compute QH118I_2 = (QH118I >= 5 & QH118I <= 9).
compute QH118I_3 = (QH118I >= 10 & QH118I <= 98).
variable labels QH118I_1 'Fur animals: 1-4' /QH118I_2 'Fur animals: 5-9' /QH118I_3 'Fur animals: 10+'.


* Beehives.
if (missing(QH118J) | QH117 <> 1) QH118J=0.
missing values QH118J (99).
compute QH118J_1 = (QH118J >= 1 & QH118J <= 4).
compute QH118J_2 = (QH118J >= 5 & QH118J <= 9).
compute QH118J_3 = (QH118J >= 10 & QH118J <= 98).
variable labels QH118J_1 'Beehives: 1-4' /QH118J_2 'Beehives: 5-9' /QH118J_3 'Beehives: 10+'.


* Ares for agricultural land.
compute landarea = QH120.
if (missing(QH120) | QH120 >= 9998) landarea = 9999.
if (missing(QH119) | QH119 <> 1) landarea=0.
missing values landarea (9999).

* Electricity.
no2zero QH121A.
* Radio.
no2zero QH121B.
* Television.
no2zero QH121C.
* Telephone (non-mobile).
no2zero QH121D.
* Computer.
no2zero QH121E.
* Refrigerator.
no2zero QH121F.
* Washing machine.
no2zero QH121G.
* Vacuum cleaner.
no2zero QH121H.
* Digital camera.
no2zero QH121I.
* Video camera/camcorder.
no2zero QH121J.
* Table/hon-tohta.
no2zero QH121K.
* Chair.
no2zero QH121L.
* Sofa/divan.
no2zero QH121M.
* Bed.
no2zero QH121N.
* Buffet/curio cabinet/wall unit.
no2zero QH121O.
* Air conditioner.
no2zero QH121P.
* DVD Player.
no2zero QH121Q.
* Satellite antenna/dish.
no2zero QH121R.
* Freezer.
no2zero QH121S.
* Electric fan.
no2zero QH121T.
* Sewing machine.
no2zero QH121U.
* Burnace -"bourgeouika".
no2zero QH121V.
* Mini-generator ("dvizhok").
no2zero QH121W.
* Fuel or wood stock.
no2zero QH121X.
* Carpet (handmade or machine made).
no2zero QH121Y.
* Connection to the Internet.
no2zero QH121Z.
* Watch.
no2zero QH122A.
* Mobile telephone.
no2zero QH122B.
* Bicycle.
no2zero QH122C.
* Motorcycle or scooter.
no2zero QH122D.
* Animal-drawn cart.
no2zero QH122E.
* Car.
no2zero QH122F.
* Boat with a motor.
no2zero QH122G.
* Truck.
no2zero QH122H.
* Tractor.
no2zero QH122I.
* Combine.
no2zero QH122J.
* Agricultural equipment.
no2zero QH122K.
* Bank account.
no2zero QH123.

* Main floor material.
dichotomize (QH142=11) QH142_11 "Main floor material: Earth/sand".
dichotomize (QH142=21) QH142_21 "Main floor material: Wood planks".
dichotomize (QH142=31) QH142_31 "Main floor material: Parquet or polished wood".
dichotomize (QH142=32) QH142_32 "Main floor material: Vinyl or linoleum".
dichotomize (QH142=33) QH142_33 "Main floor material: Ceramic tiles".
dichotomize (QH142=34) QH142_34 "Main floor material: Cement".
dichotomize (QH142=35) QH142_35 "Main floor material: Carpeted".
*ichotomize (QH142=96) QH142_96 "Main floor material: Other".


* Main roof material.
dichotomize (QH143=11) QH143_11 "Main roof material: No roof".
dichotomize (QH143=12) QH143_12 "Main roof material: Thatch/palm leaf".
dichotomize (QH143=13) QH143_13 "Main roof material: Sod".
dichotomize (QH143=23) QH143_23 "Main roof material: Wood planks".
dichotomize (QH143=24) QH143_24 "Main roof material: Cardboard".
dichotomize (QH143=31) QH143_31 "Main roof material: Metal".
dichotomize (QH143=32) QH143_32 "Main roof material: Wood".
dichotomize (QH143=33) QH143_33 "Main roof material: Schiefer/cement fiber".
dichotomize (QH143=34) QH143_34 "Main roof material: Ceramic tiles".
dichotomize (QH143=35) QH143_35 "Main roof material: Cement".
dichotomize (QH143=36) QH143_36 "Main roof material: Roofing shingles soft".
dichotomize (QH143=37) QH143_37 "Main roof material: Taule (ruberoid)".
*ichotomize (QH143=96) QH143_96 "Main roof material: Other".


* Main wall material.
dichotomize (QH144=11) QH144_11 "Main wall material: No walls".
dichotomize (QH144=12) QH144_12 "Main wall material: Cane/palm/trunks".
dichotomize (QH144=13) QH144_13 "Main wall material: Dirt".
dichotomize (QH144=22) QH144_22 "Main wall material: Stone with mud".
dichotomize (QH144=23) QH144_23 "Main wall material: Uncovered adobe".
dichotomize (QH144=24) QH144_24 "Main wall material: Plywood".
dichotomize (QH144=25) QH144_25 "Main wall material: Cardboard".
dichotomize (QH144=26) QH144_26 "Main wall material: Reused wood".
dichotomize (QH144=31) QH144_31 "Main wall material: Cement".
dichotomize (QH144=32) QH144_32 "Main wall material: Stone with lime/cement".
dichotomize (QH144=33) QH144_33 "Main wall material: Bricks".
dichotomize (QH144=34) QH144_34 "Main wall material: Cement blocks".
dichotomize (QH144=35) QH144_35 "Main wall material: Covered adobe".
dichotomize (QH144=36) QH144_36 "Main wall material: Wood planks".
dichotomize (QH144=96) QH144_96 "Main wall material: Other".

*{Members per sleeping room}.
if (hhusual=0) hhusual=hhslept.
if (QH116>0) memsleep=trunc(hhusual/QH116).
if (QH116=0) memsleep=hhusual.
if (missing(QH116) or QH116>=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=QH120N by QH120U.

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 
  QH109_11 QH109_12 QH109_13 QH109_14  QH109_21 QH109_22 QH109_23 QH109_31 QH109_41 QH109_96
  QH109_11_sh QH109_13_sh   QH109_21_sh QH109_22_sh QH109_23_sh QH109_96_sh 
  QH113_1 QH113_2 QH113_3 QH113_4 QH113_5 QH113_6 QH113_7 QH113_8 QH113_9 QH113_10 QH113_11 QH113_95 
  QH121A QH121B QH121C QH121D QH121E QH121F QH121G QH121H QH121I QH121J QH121K QH121L QH121M QH121N QH121O QH121P QH121Q QH121R QH121S QH121T QH121U QH121V
  QH121W QH121X QH121Y QH121Z QH122A QH122B QH122C QH122D QH122E QH122F QH122G QH122H QH122I QH122J QH122K QH123
  QH142_11 QH142_21 QH142_31 QH142_32 QH142_33 QH142_34 QH142_35 
  QH143_11 QH143_12 QH143_13 QH143_23 QH143_24 QH143_31 QH143_32 QH143_33 QH143_34 QH143_35 QH143_36 QH143_37 
  QH144_11 QH144_12 QH144_13 QH144_22 QH144_23 QH144_24 QH144_25 QH144_26 QH144_31 QH144_32 QH144_33 QH144_34 QH144_35 QH144_36 QH144_96
    HOUSE LAND memsleep
  QH118A_1 QH118A_2 QH118A_3 QH118B_1 QH118B_2 QH118B_3
  QH118C_1 QH118C_2 QH118C_3 QH118D_1 QH118D_2 QH118D_3
  QH118E_1 QH118E_2 QH118E_3 QH118F_1 QH118F_2 QH118F_3
  QH118G_1   QH118H_1 QH118H_2 
  QH118I_1 QH118I_2 QH118I_3 QH118J_1 QH118J_2 QH118J_3 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 
  QH109_11 QH109_12 QH109_13 QH109_14  QH109_21 QH109_22 QH109_23 QH109_31 QH109_41 QH109_96
  QH109_11_sh QH109_13_sh   QH109_21_sh QH109_22_sh QH109_23_sh QH109_96_sh 
  QH113_1 QH113_2 QH113_3 QH113_4 QH113_5 QH113_6 QH113_7 QH113_8 QH113_9 QH113_10 QH113_11 QH113_95 
  QH121A QH121B QH121C QH121D QH121E QH121F QH121G QH121H QH121I QH121J QH121K QH121L QH121M QH121N QH121O QH121P QH121Q QH121R QH121S QH121T QH121U QH121V
  QH121W QH121X QH121Y QH121Z QH122A QH122B QH122C QH122D QH122E QH122F QH122G QH122H QH122I QH122J QH122K QH123
  QH142_11 QH142_21 QH142_31 QH142_32 QH142_33 QH142_34 QH142_35 
  QH143_11 QH143_12 QH143_13 QH143_23 QH143_24 QH143_31 QH143_32 QH143_33 QH143_34 QH143_35 QH143_36 QH143_37 
  QH144_11 QH144_12 QH144_13 QH144_22 QH144_23 QH144_24 QH144_25 QH144_26 QH144_31 QH144_32 QH144_33 QH144_34 QH144_35 QH144_36 QH144_96
    HOUSE LAND memsleep
  QH118A_1 QH118A_2 QH118A_3 QH118B_1 QH118B_2 QH118B_3
  QH118C_1  QH118C_3 QH118D_1 QH118D_2 QH118D_3
  QH118E_1 QH118E_2 QH118E_3 QH118F_1 QH118F_2 QH118F_3
  QH118G_1   QH118H_1 QH118H_2 
  QH118I_1 QH118I_2 QH118I_3 QH118J_1 QH118J_2 QH118J_3 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 
  QH109_11 QH109_12 QH109_13 QH109_14  QH109_21 QH109_22 QH109_23 QH109_31 QH109_41 QH109_96
  QH109_11_sh  QH109_13_sh   QH109_21_sh QH109_22_sh QH109_23_sh  QH109_96_sh 
  QH113_1 QH113_2 QH113_3 QH113_4 QH113_5 QH113_6 QH113_7 QH113_8 QH113_9 QH113_10 QH113_11 QH113_95 
  QH121A QH121B QH121C QH121D QH121E QH121F QH121G QH121H QH121I QH121J QH121K QH121L QH121M QH121N QH121O QH121P QH121Q QH121R QH121S QH121T QH121U QH121V
  QH121W QH121X QH121Y QH121Z QH122A QH122B QH122C QH122D QH122E QH122F QH122G QH122H QH122I QH122J QH122K QH123
  QH142_11 QH142_21 QH142_31 QH142_32 QH142_33 QH142_34 QH142_35 
  QH143_11 QH143_12 QH143_13 QH143_23 QH143_24 QH143_31 QH143_32 QH143_33 QH143_34 QH143_35 QH143_36 QH143_37 
  QH144_11 QH144_12 QH144_13 QH144_22 QH144_23 QH144_24 QH144_25 QH144_26 QH144_31 QH144_32 QH144_33 QH144_34 QH144_35 QH144_36 QH144_96
    HOUSE LAND memsleep
  QH118A_1 QH118A_2 QH118A_3 QH118B_1 QH118B_2 QH118B_3
  QH118C_1  QH118C_3 QH118D_1 QH118D_2 QH118D_3
  QH118E_1 QH118E_2 QH118E_3 QH118F_1 QH118F_2 QH118F_3
  QH118G_1   QH118H_1 QH118H_2 
  QH118I_1 QH118I_2 QH118I_3 QH118J_1 QH118J_2 QH118J_3 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
** Any others ?.

*** 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 
  QH109_11 QH109_12 QH109_13 QH109_14  QH109_21 QH109_22 QH109_23 QH109_31 QH109_41 QH109_96
  QH109_11_sh  QH109_13_sh   QH109_21_sh QH109_22_sh QH109_23_sh   QH109_96_sh 
  QH113_1 QH113_2 QH113_3 QH113_4 QH113_5 QH113_6 QH113_7 QH113_8 QH113_9 QH113_10 QH113_11 QH113_95 
  QH121A QH121B QH121C QH121D QH121E QH121F QH121G QH121H QH121I QH121J QH121K QH121L QH121M QH121N QH121O QH121P QH121Q QH121R QH121S QH121T QH121U QH121V
  QH121W QH121X QH121Y QH121Z QH122A QH122B QH122C QH122D QH122E QH122F QH122G QH122H QH122I QH122J QH122K QH123
  QH142_11 QH142_21 QH142_31 QH142_32 QH142_33 QH142_34 QH142_35 
  QH143_11 QH143_12 QH143_13 QH143_23 QH143_24 QH143_31 QH143_32 QH143_33 QH143_34 QH143_35 QH143_36 QH143_37 
  QH144_11 QH144_12 QH144_13 QH144_22 QH144_23 QH144_24 QH144_25 QH144_26 QH144_31 QH144_32 QH144_33 QH144_34 QH144_35 QH144_36 QH144_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 
  QH109_11 QH109_12 QH109_13 QH109_14  QH109_21 QH109_22 QH109_23 QH109_31 QH109_41 QH109_96
  QH109_11_sh QH109_13_sh   QH109_21_sh QH109_22_sh QH109_23_sh   QH109_96_sh 
  QH113_1 QH113_2 QH113_3 QH113_4 QH113_5 QH113_6 QH113_7 QH113_8 QH113_9 QH113_10 QH113_11 QH113_95 
  QH121A QH121B QH121C QH121D QH121E QH121F QH121G QH121H QH121I QH121J QH121K QH121L QH121M QH121N QH121O QH121P QH121Q QH121R QH121S QH121T QH121U QH121V
  QH121W QH121X QH121Y QH121Z QH122A QH122B QH122C QH122D QH122E QH122F QH122G QH122H QH122I QH122J QH122K QH123
  QH142_11 QH142_21 QH142_31 QH142_32 QH142_33 QH142_34 QH142_35 
  QH143_11 QH143_12 QH143_13 QH143_23 QH143_24 QH143_31 QH143_32 QH143_33 QH143_34 QH143_35 QH143_36 QH143_37 
  QH144_11 QH144_12 QH144_13 QH144_22 QH144_23 QH144_24 QH144_25 QH144_26 QH144_31 QH144_32 QH144_33 QH144_34 QH144_35 QH144_36 QH144_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.

* removed QH109_51 QH109_61 QH113_5 QH113_6 QH144_11 QH144_12 QH118B_2 QH118C_3 QH118G_1 QH118I_3.
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 
  QH109_11 QH109_12 QH109_13 QH109_14  QH109_21 QH109_22 QH109_23 QH109_31 QH109_41 QH109_96
  QH109_11_sh  QH109_13_sh   QH109_21_sh QH109_22_sh QH109_23_sh  QH109_96_sh 
  QH113_1 QH113_2 QH113_3 QH113_4   QH113_7 QH113_8 QH113_9 QH113_10 QH113_11 QH113_95 
  QH121A QH121B QH121C QH121D QH121E QH121F QH121G QH121H QH121I QH121J QH121K QH121L QH121M QH121N QH121O QH121P QH121Q QH121R QH121S QH121T QH121U QH121V
  QH121W QH121X QH121Y QH121Z QH122A QH122B QH122C QH122D QH122E QH122F QH122G QH122H QH122I QH122J QH122K QH123
  QH142_11 QH142_21 QH142_31 QH142_32 QH142_33 QH142_34 QH142_35 
  QH143_11 QH143_12 QH143_13 QH143_23 QH143_24 QH143_31 QH143_32 QH143_33 QH143_34 QH143_35 QH143_36 QH143_37 
     QH144_13 QH144_22 QH144_23 QH144_24 QH144_25 QH144_26 QH144_31 QH144_32 QH144_33 QH144_34 QH144_35 QH144_36 QH144_96
    HOUSE LAND memsleep
  QH118A_1 QH118A_2 QH118A_3 QH118B_1   QH118B_3
  QH118C_1    QH118D_1 QH118D_2 QH118D_3
  QH118E_1 QH118E_2 QH118E_3 QH118F_1 QH118F_2 QH118F_3
      QH118H_1 QH118H_2 
  QH118I_1 QH118I_2   QH118J_1 QH118J_2 QH118J_3 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 
  QH109_11 QH109_12 QH109_13 QH109_14  QH109_21 QH109_22 QH109_23 QH109_31 QH109_41 QH109_96
  QH109_11_sh QH109_13_sh   QH109_21_sh QH109_22_sh QH109_23_sh   QH109_96_sh 
  QH113_1 QH113_2 QH113_3 QH113_4   QH113_7 QH113_8 QH113_9 QH113_10 QH113_11 QH113_95 
  QH121A QH121B QH121C QH121D QH121E QH121F QH121G QH121H QH121I QH121J QH121K QH121L QH121M QH121N QH121O QH121P QH121Q QH121R QH121S QH121T QH121U QH121V
  QH121W QH121X QH121Y QH121Z QH122A QH122B QH122C QH122D QH122E QH122F QH122G QH122H QH122I QH122J QH122K QH123
  QH142_11 QH142_21 QH142_31 QH142_32 QH142_33 QH142_34 QH142_35 
  QH143_11 QH143_12 QH143_13 QH143_23 QH143_24 QH143_31 QH143_32 QH143_33 QH143_34 QH143_35 QH143_36 QH143_37 
     QH144_13 QH144_22 QH144_23 QH144_24 QH144_25 QH144_26 QH144_31 QH144_32 QH144_33 QH144_34 QH144_35 QH144_36 QH144_96
    HOUSE LAND memsleep
  QH118A_1 QH118A_2 QH118A_3 QH118B_1   QH118B_3
  QH118C_1    QH118D_1 QH118D_2 QH118D_3
  QH118E_1 QH118E_2 QH118E_3 QH118F_1 QH118F_2 QH118F_3
      QH118H_1 QH118H_2 
  QH118I_1 QH118I_2   QH118J_1 QH118J_2 QH118J_3 landarea
  /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.

* removed QH109_11_sh QH109_13_sh QH109_96_sh QH143_24 QH144_96.
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 
  QH109_11 QH109_12 QH109_13 QH109_14  QH109_21 QH109_22 QH109_23 QH109_31 QH109_41 QH109_96
        QH109_21_sh QH109_22_sh QH109_23_sh 
  QH113_1 QH113_2 QH113_3 QH113_4 QH113_5 QH113_6 QH113_7 QH113_8 QH113_9 QH113_10 QH113_11 QH113_95 
  QH121A QH121B QH121C QH121D QH121E QH121F QH121G QH121H QH121I QH121J QH121K QH121L QH121M QH121N QH121O QH121P QH121Q QH121R QH121S QH121T QH121U QH121V
  QH121W QH121X QH121Y QH121Z QH122A QH122B QH122C QH122D QH122E QH122F QH122G QH122H QH122I QH122J QH122K QH123
  QH142_11 QH142_21 QH142_31 QH142_32 QH142_33 QH142_34 QH142_35 
  QH143_11 QH143_12 QH143_13 QH143_23   QH143_31 QH143_32 QH143_33 QH143_34 QH143_35 QH143_36 QH143_37 
  QH144_11 QH144_12 QH144_13 QH144_22 QH144_23 QH144_24 QH144_25 QH144_26 QH144_31 QH144_32 QH144_33 QH144_34 QH144_35 QH144_36 
    HOUSE LAND memsleep
  QH118A_1 QH118A_2 QH118A_3 QH118B_1 QH118B_2 QH118B_3
  QH118C_1  QH118C_3 QH118D_1 QH118D_2 QH118D_3
  QH118E_1 QH118E_2 QH118E_3 QH118F_1 QH118F_2 QH118F_3
  QH118G_1   QH118H_1 QH118H_2 
  QH118I_1 QH118I_2 QH118I_3 QH118J_1 QH118J_2 QH118J_3 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 
  QH109_11 QH109_12 QH109_13 QH109_14  QH109_21 QH109_22 QH109_23 QH109_31 QH109_41 QH109_96
      QH109_21_sh QH109_22_sh QH109_23_sh 
  QH113_1 QH113_2 QH113_3 QH113_4 QH113_5 QH113_6 QH113_7 QH113_8 QH113_9 QH113_10 QH113_11 QH113_95 
  QH121A QH121B QH121C QH121D QH121E QH121F QH121G QH121H QH121I QH121J QH121K QH121L QH121M QH121N QH121O QH121P QH121Q QH121R QH121S QH121T QH121U QH121V
  QH121W QH121X QH121Y QH121Z QH122A QH122B QH122C QH122D QH122E QH122F QH122G QH122H QH122I QH122J QH122K QH123
  QH142_11 QH142_21 QH142_31 QH142_32 QH142_33 QH142_34 QH142_35 
  QH143_11 QH143_12 QH143_13 QH143_23   QH143_31 QH143_32 QH143_33 QH143_34 QH143_35 QH143_36 QH143_37 
  QH144_11 QH144_12 QH144_13 QH144_22 QH144_23 QH144_24 QH144_25 QH144_26 QH144_31 QH144_32 QH144_33 QH144_34 QH144_35 QH144_36 
    HOUSE LAND memsleep
  QH118A_1 QH118A_2 QH118A_3 QH118B_1 QH118B_2 QH118B_3
  QH118C_1  QH118C_3 QH118D_1 QH118D_2 QH118D_3
  QH118E_1 QH118E_2 QH118E_3 QH118F_1 QH118F_2 QH118F_3
  QH118G_1   QH118H_1 QH118H_2 
  QH118I_1 QH118I_2 QH118I_3 QH118J_1 QH118J_2 QH118J_3 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'.

* Reverse the urban score - added 1/2/2018 - TC.
compute urbscore = 0 - urbscore.

* 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+
  QH109_11+QH109_12+QH109_13+QH109_14+QH109_21+QH109_22+QH109_23+QH109_31+QH109_41+QH109_96+
  QH109_11_sh+QH109_13_sh+QH109_21_sh+QH109_22_sh+QH109_23_sh+
  QH113_1+QH113_2+QH113_3+QH113_4+QH113_5+QH113_6+QH113_7+QH113_8+QH113_9+QH113_10+QH113_11+QH113_95+
  QH121A+QH121B+QH121C+QH121D+QH121E+QH121F+QH121G+QH121H+QH121I+QH121J+QH121K+QH121L+QH121M+QH121N+QH121O+QH121P+QH121Q+QH121R+QH121S+QH121T+QH121U+QH121V+
  QH121W+QH121X+QH121Y+QH121Z+QH122A+QH122B+QH122C+QH122D+QH122E+QH122F+QH122G+QH122H+QH122I+QH122J+QH122K+QH123+
  QH142_11+QH142_21+QH142_31+QH142_32+QH142_33+QH142_34+QH142_35+
  QH143_11+QH143_12+QH143_13+QH143_23+QH143_24+QH143_31+QH143_32+QH143_33+QH143_34+QH143_35+QH143_36+QH143_37+
  QH144_11+QH144_12+QH144_13+QH144_22+QH144_23+QH144_24+QH144_25+QH144_26+QH144_31+QH144_32+QH144_33+QH144_34+QH144_35+QH144_36+QH144_96+
    HOUSE+LAND+memsleep+
  QH118A_1+QH118A_2+QH118A_3+QH118B_1+QH118B_2+QH118B_3+
  QH118C_1+QH118C_3+QH118D_1+QH118D_2+QH118D_3+
  QH118E_1+QH118E_2+QH118E_3+QH118F_1+QH118F_2+QH118F_3+
  QH118G_1+QH118H_1+QH118H_2+
  QH118I_1+QH118I_2+QH118I_3+QH118J_1+QH118J_2+QH118J_3+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 
  QH109_11 QH109_12 QH109_13 QH109_14  QH109_21 QH109_22 QH109_23 QH109_31 QH109_41 QH109_51 QH109_61  QH109_96
  QH109_11_sh QH109_13_sh   QH109_21_sh QH109_22_sh QH109_23_sh QH109_51_sh 
  QH113_1 QH113_2 QH113_3 QH113_4 QH113_5 QH113_6 QH113_7 QH113_8 QH113_9 QH113_10 QH113_11 QH113_95 
  QH121A QH121B QH121C QH121D QH121E QH121F QH121G QH121H QH121I QH121J QH121K QH121L QH121M QH121N QH121O QH121P QH121Q QH121R QH121S QH121T QH121U QH121V
  QH121W QH121X QH121Y QH121Z QH122A QH122B QH122C QH122D QH122E QH122F QH122G QH122H QH122I QH122J QH122K QH123
  QH142_11 QH142_21 QH142_31 QH142_32 QH142_33 QH142_34 QH142_35 
  QH143_11 QH143_12 QH143_13 QH143_23 QH143_24 QH143_31 QH143_32 QH143_33 QH143_34 QH143_35 QH143_36 QH143_37 
  QH144_11 QH144_12 QH144_13 QH144_22 QH144_23 QH144_24 QH144_25 QH144_26 QH144_31 QH144_32 QH144_33 QH144_34 QH144_35 QH144_36 QH144_96
    HOUSE LAND memsleep
  QH118A_1 QH118A_2 QH118A_3 QH118B_1 QH118B_2 QH118B_3
  QH118C_1  QH118C_3 QH118D_1 QH118D_2 QH118D_3
  QH118E_1 QH118E_2 QH118E_3 QH118F_1 QH118F_2 QH118F_3
  QH118G_1   QH118H_1 QH118H_2 
  QH118I_1 QH118I_2 QH118I_3 QH118J_1 QH118J_2 QH118J_3 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 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, Tajikistan DHS 2016-17'
  corner='Residence/region' /slabels visible=no.