* Wealth index calculation. Mamadou Diallo, 05/03/2018. Burkina Faso MIS 2017-18.
cd "C:\Users\21180\OneDrive - ICF\Projects\Analysis\Wealth Index Construction\BF2017\wealth".
*cd 'C:\BF7A\Wealth'.
include file='Wealth_assets.sps'.
missing values QH113 (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 (QH106=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 d'eau à boire.
dichotomize (QH101=11) QH101_11 "Source d'eau à boire: Robinet - dans le logement".
dichotomize (QH101=12) QH101_12 "Source d'eau à boire: Robinet - dans cour/parcelle".
dichotomize (QH101=13) QH101_13 "Source d'eau à boire: Robinet - chez un voisin".
dichotomize (QH101=14) QH101_14 "Source d'eau à boire: Robinet - public / borne fontaine".
dichotomize (QH101=21) QH101_21 "Source d'eau à boire: Puits à pompe ou forage".
dichotomize (QH101=31) QH101_31 "Source d'eau à boire: Puits creusé - protégé".
dichotomize (QH101=32) QH101_32 "Source d'eau à boire: Puits creusé - non protégé".
dichotomize (QH101=41) QH101_41 "Source d'eau à boire: Source - protégé".
dichotomize (QH101=42) QH101_42 "Source d'eau à boire: Source - non protégé".
*ichotomize (QH101=51) QH101_51 "Source d'eau à boire: Eau de pluie".
*ichotomize (QH101=61) QH101_61 "Source d'eau à boire: Camion citerne".
dichotomize (QH101=71) QH101_71 "Source d'eau à boire: Charrette avec petite citerne/ tonneau".
dichotomize (QH101=81) QH101_81 "Source d'eau à boire: Eau de surface (rivière/barrage/lac/mare/fleuve/canal/canal d'irrigation)".
dichotomize (QH101=91) QH101_91 "Source d'eau à boire: Eau de bouteille".
dichotomize (QH101=96) QH101_96 "Source d'eau à boire: Autre".


* Type de toilettes.
dichotomize (QH105=11) QH105_11 "Type de toilettes: Chasse d'eau connectée - à un système d'égout".
dichotomize (QH105=12) QH105_12 "Type de toilettes: Chasse d'eau connectée - à une fosse septique".
dichotomize (QH105=13 | QH105 = 15) QH105_13 "Type de toilettes: Chasse d'eau connectée - à une fosse d'aisances/à ne sait pas où".
*ichotomize (QH105=14) QH105_14 "Type de toilettes: Chasse d'eau connectée - à quelque chose d'autre".
*ichotomize (QH105=15) QH105_15 "Type de toilettes: Chasse d'eau connectée - à ne sait pas où".
dichotomize (QH105=21) QH105_21 "Type de toilettes: Fosses/latrines - améliorées auto-aérées".
dichotomize (QH105=22) QH105_22 "Type de toilettes: Fosses/latrines - avec dalle lavable".
dichotomize (QH105=23) QH105_23 "Type de toilettes: Fosses/latrines - sans dalle / trou ouvert".
dichotomize (QH105=31 | QH105=41 | QH105=51) QH105_31 "Type de toilettes: Toilettes à compostage/tinette/suspendus".
*ichotomize (QH105=41) QH105_41 "Type de toilettes: Seau/tinette".
*ichotomize (QH105=51) QH105_51 "Type de toilettes: Toilettes/latrines suspendues".
dichotomize (QH105=61) QH105_61 "Type de toilettes: Pas de toilettes / nature".
dichotomize (QH105=96) QH105_96 "Type de toilettes: Autre".

*hared_fac QH105_11 QH105_11_sh "Type de toilettes: Chasse d'eau connectée - à un système d'égout - shared".
shared_fac QH105_12 QH105_12_sh "Type de toilettes: Chasse d'eau connectée - à une fosse septique - shared".
shared_fac QH105_13 QH105_13_sh "Type de toilettes: Chasse d'eau connectée - à une fosse d'aisances - shared/à ne sait pas où".
*hared_fac QH105_14 QH105_14_sh "Type de toilettes: Chasse d'eau connectée - à quelque chose d'autre - shared".
*hared_fac QH105_15  "Type de toilettes: Chasse d'eau connectée - à ne sait pas où - shared".
shared_fac QH105_21 QH105_21_sh "Type de toilettes: Fosses/latrines - améliorées auto-aérées - shared".
shared_fac QH105_22 QH105_22_sh "Type de toilettes: Fosses/latrines - avec dalle lavable - shared".
shared_fac QH105_23 QH105_23_sh "Type de toilettes: Fosses/latrines - sans dalle / trou ouvert - shared".
shared_fac QH105_31 QH105_31_sh "Type de toilettes: Toilettes à compostage/tinette/suspendus - shared".
*hared_fac QH105_41  "Type de toilettes: Seau/tinette - shared".
*hared_fac QH105_51 QH105_51_sh "Type de toilettes: Toilettes/latrines suspendues - shared".
shared_fac QH105_96 QH105_96_sh "Type de toilettes: Autre - shared".


* Type de combustible.
*ichotomize (QH108=1) QH108_1 "Type de combustible: Electricité".
dichotomize (QH108=2) QH108_2 "Type de combustible: Gaz propane liquifié (GPL)".
dichotomize (QH108=3) QH108_3 "Type de combustible: Gaz naturel".
dichotomize (QH108=4) QH108_4 "Type de combustible: Biogaz".
*ichotomize (QH108=5) QH108_5 "Type de combustible: Kerosène".
dichotomize (QH108=6) QH108_6 "Type de combustible: Charbon, lignite".
dichotomize (QH108=7) QH108_7 "Type de combustible: Charbon de bois".
dichotomize (QH108=8) QH108_8 "Type de combustible: Bois".
dichotomize (QH108=9) QH108_9 "Type de combustible: Pailles/branchages/herbes".
dichotomize (QH108=10) QH108_10 "Type de combustible: Résidus agricoles".
dichotomize (QH108=11) QH108_11 "Type de combustible: Bouse".
dichotomize (QH108=95) QH108_95 "Type de combustible: Pas de repasd préparé dans le ménage".
dichotomize (QH108=96) QH108_96 "Type de combustible: Autre".


* Vaches/taureaux.
if (missing(QH111A) | QH111A = 98 | QH110 <> 1) QH111A=0.
missing values QH111A (99).
compute QH111A_1 = (QH111A >= 1 & QH111A <= 4).
compute QH111A_2 = (QH111A >= 5 & QH111A <= 9).
compute QH111A_3 = (QH111A >= 10 & QH111A <= 95).
variable labels QH111A_1 'Vaches/taureaux: 1-4' /QH111A_2 'Vaches/taureaux: 5-9' /QH111A_3 'Vaches/taureaux: 10+'.


* Autre bétail.
if (missing(QH111B) | QH111B = 98 | QH110 <> 1) QH111B=0.
missing values QH111B (99).
compute QH111B_1 = (QH111B >= 1 & QH111B <= 9).
compute QH111B_2 = (QH111B >= 10 & QH111B <= 29).
compute QH111B_3 = (QH111B >= 30 & QH111B <= 95).
variable labels QH111B_1 'Autre bétail: 1-9' /QH111B_2 'Autre bétail: 10-29' /QH111B_3 'Autre bétail: 30+'.


* Chevaux/ânes/mules.
if (missing(QH111C) | QH111C = 98 | QH110 <> 1) QH111C=0.
missing values QH111C (99).
compute QH111C_1 = (QH111C >= 1 & QH111C <= 4).
compute QH111C_2 = (QH111C >= 5 & QH111C <= 9).
compute QH111C_3 = (QH111C >= 10 & QH111C <= 95).
variable labels QH111C_1 'Chevaux/ânes/mules: 1-4' /QH111C_2 'Chevaux/ânes/mules: 5-9' /QH111C_3 'Chevaux/ânes/mules: 10+'.


* Chèvres.
if (missing(QH111D) | QH111D = 98 | QH110 <> 1) QH111D=0.
missing values QH111D (99).
compute QH111D_1 = (QH111D >= 1 & QH111D <= 4).
compute QH111D_2 = (QH111D >= 5 & QH111D <= 9).
compute QH111D_3 = (QH111D >= 10 & QH111D <= 95).
variable labels QH111D_1 'Chèvres: 1-4' /QH111D_2 'Chèvres: 5-9' /QH111D_3 'Chèvres: 10+'.


* Moutons.
if (missing(QH111E) | QH111E = 98 | QH110 <> 1) QH111E=0.
missing values QH111E (99).
compute QH111E_1 = (QH111E >= 1 & QH111E <= 4).
compute QH111E_2 = (QH111E >= 5 & QH111E <= 9).
compute QH111E_3 = (QH111E >= 10 & QH111E <= 95).
variable labels QH111E_1 'Moutons: 1-4' /QH111E_2 'Moutons: 5-9' /QH111E_3 'Moutons: 10+'.


* Poulets/autre volaille.
if (missing(QH111F) | QH111F = 98 | QH110 <> 1) QH111F=0.
missing values QH111F (99).
compute QH111F_1 = (QH111F >= 1 & QH111F <= 9).
compute QH111F_2 = (QH111F >= 10 & QH111F <= 29).
compute QH111F_3 = (QH111F >= 30 & QH111F <= 95).
variable labels QH111F_1 'Poulets/autre volaille: 1-9' /QH111F_2 'Poulets/autre volaille: 10-29' /QH111F_3 'Poulets/autre volaille: 30+'.


* Porcs.
if (missing(QH111G) | QH111G = 98 | QH110 <> 1) QH111G=0.
missing values QH111G (99).
compute QH111G_1 = (QH111G >= 1 & QH111G <= 4).
compute QH111G_2 = (QH111G >= 5 & QH111G <= 9).
compute QH111G_3 = (QH111G >= 10 & QH111G <= 95).
variable labels QH111G_1 'Porcs: 1-4' /QH111G_2 'Porcs: 5-9' /QH111G_3 'Porcs: 10+'.


* Hectares de terres cultivables.
compute landarea = QH113.
if (missing(QH113) | QH113 >= 99.8) landarea = 99.9.
if (missing(QH112) | QH112 <> 1) landarea=0.
missing values landarea (99.9).
* Electricité.
no2zero QH114A.
* Radio.
no2zero QH114B.
* Television.
no2zero QH114C.
* Telephone fixe.
no2zero QH114D.
* Ordinateur.
no2zero QH114E.
* Refrigerateur/congélateur.
no2zero QH114F.
* Table/chaise.
no2zero QH114G.
* Armoire/bibliothèque.
no2zero QH114H.
* Cuisinière/rechaud.
no2zero QH114I.
* Fusil de chasse.
no2zero QH114J.
* Charrue.
no2zero QH114K.
* Montre.
no2zero QH115A.
* Telephone portable.
no2zero QH115B.
* Bicyclette.
no2zero QH115C.
* Motorcyclette/scooter.
no2zero QH115D.
* Charrette avec animal.
no2zero QH115E.
* Voiture/camionnette.
no2zero QH115F.
* Bateau à moteur.
no2zero QH115G.
* Pirogue.
no2zero QH115H.
* recode bateau motor into pirogue.
if (QH115G = 1) QH115H = 1.
* Compte en banque.
no2zero QH116.

* Principal matériau du sol du logement.
dichotomize (QH131=11) QH131_11 "Principal matériau du sol du logement: Terre/sable".
dichotomize (QH131=12) QH131_12 "Principal matériau du sol du logement: Bouse".
*ichotomize (QH131=21) QH131_21 "Principal matériau du sol du logement: Planches en bois".
*ichotomize (QH131=22) QH131_22 "Principal matériau du sol du logement: Palmes/bambou".
*ichotomize (QH131=31) QH131_31 "Principal matériau du sol du logement: Parquet ou bois ciré".
*ichotomize (QH131=32) QH131_32 "Principal matériau du sol du logement: Bandes de vinyle/asphalte".
dichotomize (QH131=33) QH131_33 "Principal matériau du sol du logement: Carrelage/carreaux".
dichotomize (QH131=34) QH131_34 "Principal matériau du sol du logement: Ciment".
dichotomize (QH131=35) QH131_35 "Principal matériau du sol du logement: Moquette".
*ichotomize (QH131=96)  QH131_96 "Principal matériau du sol du logement: Autre".


* Principal matériau du toi du logement.
dichotomize (QH132=11) QH132_11 "Principal matériau du toi du logement: Pas de toit".
dichotomize (QH132=12) QH132_12 "Principal matériau du toi du logement: Chaume/palmes/feuilles".
dichotomize (QH132=13) QH132_13 "Principal matériau du toi du logement: Mottes de terre".
dichotomize (QH132=21 | QH132=22) QH132_21 "Principal matériau du toi du logement: Natte/Palmes/bambou".
*ichotomize (QH132=22) QH132_22 "Principal matériau du toi du logement: Palmes/bambou".
dichotomize (QH132=23 | QH132=24) QH132_23 "Principal matériau du toi du logement: Planches en bois/Carton".
*ichotomize (QH132=24) QH132_24 "Principal matériau du toi du logement: Carton".
dichotomize (QH132=31) QH132_31 "Principal matériau du toi du logement: Tôle".
dichotomize (QH132=32 | QH132=34) QH132_32 "Principal matériau du toi du logement: Bois/Tuiles".
*ichotomize (QH132=33) QH132_33 "Principal matériau du toi du logement: Zinc/fibre de ciment".
*ichotomize (QH132=34) QH132_34 "Principal matériau du toi du logement: Tuiles".
dichotomize (QH132=35) QH132_35 "Principal matériau du toi du logement: Ciment".
*ichotomize (QH132=36) QH132_36 "Principal matériau du toi du logement: Shingles".
*ichotomize (QH132=96) QH132_96 "Principal matériau du toi du logement: Autre".


* Principal matériau des murs exterieurs du logement.
dichotomize (QH133=11) QH133_11 "Principal matériau des murs exterieurs du logement: Pas de mur".
dichotomize (QH133=12) QH133_12 "Principal matériau des murs exterieurs du logement: Bambou/cane/palme/tronc".
dichotomize (QH133=13) QH133_13 "Principal matériau des murs exterieurs du logement: Terre".
dichotomize (QH133=21) QH133_21 "Principal matériau des murs exterieurs du logement: Bambou avec boue".
dichotomize (QH133=22 | QH133 = 23) QH133_22 "Principal matériau des murs exterieurs du logement: Pierres avec boue/Adobe non recouvert".
*ichotomize (QH133=23) QH133_23 "Principal matériau des murs exterieurs du logement: Adobe non recouvert".
*ichotomize (QH133=24) QH133_24 "Principal matériau des murs exterieurs du logement: Contre-plaqué".
*ichotomize (QH133=25) QH133_25 "Principal matériau des murs exterieurs du logement: Carton".
*ichotomize (QH133=26) QH133_26 "Principal matériau des murs exterieurs du logement: Bois de récupération".
dichotomize (QH133=31) QH133_31 "Principal matériau des murs exterieurs du logement: Ciment".
dichotomize (QH133=32) QH133_32 "Principal matériau des murs exterieurs du logement: Pierres avec chaux / ciment".
dichotomize (QH133=33) QH133_33 "Principal matériau des murs exterieurs du logement: Briques".
dichotomize (QH133=34 | QH133=35) QH133_34 "Principal matériau des murs exterieurs du logement: Blocs de ciment/Adobe recouvert".
*ichotomize (QH133=35) QH133_35 "Principal matériau des murs exterieurs du logement: Adobe recouvert".
*ichotomize (QH133=36) QH133_36 "Principal matériau des murs exterieurs du logement: Planches en bois/shingles".
dichotomize (QH133=96) QH133_96 "Principal matériau des murs exterieurs du logement: Autre".

*{Members per sleeping room}.
if (hhusual=0) hhusual=hhslept.
if (QH109>0) memsleep=trunc(hhusual/QH109).
if (QH109=0) memsleep=hhusual.
if (missing(QH109) or QH109>=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 QH133.

* Toilet facility by shared/not shared.
crosstabs /tables=QH105 by QH106.

* Land area by units - if there are separate units - need to convert them to one unit.
*crosstabs /tables=QH113N by QH113U.

frequencies variables=
  QH101_11 QH101_12 QH101_13 QH101_14 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42   QH101_71 QH101_81 QH101_91 QH101_96
  QH105_11 QH105_12 QH105_13   QH105_21 QH105_22 QH105_23 QH105_31   QH105_61 QH105_96
   QH105_12_sh QH105_13_sh   QH105_21_sh QH105_22_sh QH105_23_sh QH105_31_sh   QH105_96_sh
   QH108_2 QH108_3 QH108_4 QH108_6 QH108_7 QH108_8 QH108_9 QH108_10 QH108_11 QH108_95 QH108_96
  QH114A QH114B QH114C QH114D QH114E QH114F QH114G QH114H QH114I QH114J QH114K QH115A QH115B QH115C QH115D QH115E QH115F  QH115H QH116
  QH131_11 QH131_12     QH131_33 QH131_34 QH131_35  
  QH132_11 QH132_12 QH132_13 QH132_21  QH132_23  QH132_31 QH132_32   QH132_35  
  QH133_11 QH133_12 QH133_13 QH133_21 QH133_22     QH133_31 QH133_32 QH133_33 QH133_34 QH133_96  
  memsleep
  QH111A_1 QH111A_2 QH111A_3 QH111B_1 QH111B_2 QH111B_3
  QH111C_1 QH111C_2 QH111C_3 QH111D_1 QH111D_2 QH111D_3
  QH111E_1 QH111E_2 QH111E_3 QH111F_1 QH111F_2 QH111F_3
  QH111G_1 QH111G_2 QH111G_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.

* Variables removed totally from PCA analysis.
* QH101_51 QH101_61 QH105_14 QH105_14_sh QH105_15  QH105_41  QH105_51 QH105_51_sh QH105_11_sh.
* QH108_1 QH108_5 QH115G QH131_21 QH131_22 QH131_31 QH131_32 QH131_96.
* QH132_22 QH132_24 QH132_33 QH132_34 QH132_36 QH132_96.
* QH133_23 QH133_24 QH133_25 QH133_26 QH133_35 QH133_36

factor /variables 
  QH101_11 QH101_12 QH101_13 QH101_14 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42   QH101_71 QH101_81 QH101_91 QH101_96
  QH105_11 QH105_12 QH105_13   QH105_21 QH105_22 QH105_23 QH105_31   QH105_61 QH105_96 
   QH105_12_sh QH105_13_sh   QH105_21_sh QH105_22_sh QH105_23_sh QH105_31_sh   QH105_96_sh
   QH108_2 QH108_3 QH108_4 QH108_6 QH108_7 QH108_8 QH108_9 QH108_10 QH108_11 QH108_95 QH108_96
  QH114A QH114B QH114C QH114D QH114E QH114F QH114G QH114H QH114I QH114J QH114K QH115A QH115B QH115C QH115D QH115E QH115F  QH115H QH116
  QH131_11 QH131_12     QH131_33 QH131_34 QH131_35  
  QH132_11 QH132_12 QH132_13 QH132_21  QH132_23  QH132_31 QH132_32   QH132_35  
  QH133_11 QH133_12 QH133_13 QH133_21 QH133_22     QH133_31 QH133_32 QH133_33 QH133_34   QH133_96
   memsleep
  QH111A_1 QH111A_2 QH111A_3 QH111B_1 QH111B_2 QH111B_3
  QH111C_1 QH111C_2 QH111C_3 QH111D_1 QH111D_2 QH111D_3
  QH111E_1 QH111E_2 QH111E_3 QH111F_1 QH111F_2 QH111F_3
  QH111G_1 QH111G_2 QH111G_3 landarea
  /missing meansub
  /analysis
  QH101_11 QH101_12 QH101_13 QH101_14 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42   QH101_71 QH101_81 QH101_91 QH101_96
  QH105_11 QH105_12 QH105_13   QH105_21 QH105_22 QH105_23 QH105_31   QH105_61 QH105_96 
   QH105_12_sh QH105_13_sh   QH105_21_sh QH105_22_sh QH105_23_sh QH105_31_sh   QH105_96_sh
   QH108_2 QH108_3 QH108_4 QH108_6 QH108_7 QH108_8 QH108_9 QH108_10 QH108_11 QH108_95 QH108_96
  QH114A QH114B QH114C QH114D QH114E QH114F QH114G QH114H QH114I QH114J QH114K QH115A QH115B QH115C QH115D QH115E QH115F  QH115H QH116
  QH131_11 QH131_12     QH131_33 QH131_34 QH131_35  
  QH132_11 QH132_12 QH132_13 QH132_21  QH132_23  QH132_31 QH132_32   QH132_35  
  QH133_11 QH133_12 QH133_13 QH133_21 QH133_22     QH133_31 QH133_32 QH133_33 QH133_34   QH133_96
   memsleep
  QH111A_1 QH111A_2 QH111A_3 QH111B_1 QH111B_2 QH111B_3
  QH111C_1 QH111C_2 QH111C_3 QH111D_1 QH111D_2 QH111D_3
  QH111E_1 QH111E_2 QH111E_3 QH111F_1 QH111F_2 QH111F_3
  QH111G_1 QH111G_2 QH111G_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_71 QH101_81 QH101_91 QH101_96
  QH105_11 QH105_12 QH105_13   QH105_21 QH105_22 QH105_23 QH105_31   QH105_61 QH105_96
   QH105_12_sh QH105_13_sh   QH105_21_sh QH105_22_sh QH105_23_sh QH105_31_sh   QH105_96_sh
   QH108_2 QH108_3 QH108_4 QH108_6 QH108_7 QH108_8 QH108_9 QH108_10 QH108_11 QH108_95 QH108_96
  QH114A QH114B QH114C QH114D QH114E QH114F QH114G QH114H QH114I QH114J QH114K QH115A QH115B QH115C QH115D QH115E QH115F  QH115H QH116
  QH131_11 QH131_12     QH131_33 QH131_34 QH131_35  
  QH132_11 QH132_12 QH132_13 QH132_21  QH132_23  QH132_31 QH132_32   QH132_35  
  QH133_11 QH133_12 QH133_13 QH133_21 QH133_22     QH133_31 QH133_32 QH133_33 QH133_34   QH133_96
   memsleep
  /missing meansub
  /analysis
  QH101_11 QH101_12 QH101_13 QH101_14 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42   QH101_71 QH101_81 QH101_91 QH101_96
  QH105_11 QH105_12 QH105_13   QH105_21 QH105_22 QH105_23 QH105_31   QH105_61 QH105_96
   QH105_12_sh QH105_13_sh   QH105_21_sh QH105_22_sh QH105_23_sh QH105_31_sh   QH105_96_sh
   QH108_2 QH108_3 QH108_4 QH108_6 QH108_7 QH108_8 QH108_9 QH108_10 QH108_11 QH108_95 QH108_96
  QH114A QH114B QH114C QH114D QH114E QH114F QH114G QH114H QH114I QH114J QH114K QH115A QH115B QH115C QH115D QH115E QH115F  QH115H QH116
  QH131_11 QH131_12     QH131_33 QH131_34 QH131_35  
  QH132_11 QH132_12 QH132_13 QH132_21  QH132_23  QH132_31 QH132_32   QH132_35  
  QH133_11 QH133_12 QH133_13 QH133_21 QH133_22     QH133_31 QH133_32 QH133_33 QH133_34   QH133_96
   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.

* Variables removed from urban for PCA analysis.
* QH101_81 QH105_31 QH105_31_SH QH105_96 QH108_9 QH108_10 QH108_11 QH111C_3  QH133_12.

factor /variables
  QH101_11 QH101_12 QH101_13 QH101_14 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42   QH101_71  QH101_91 QH101_96
  QH105_11 QH105_12 QH105_13   QH105_21 QH105_22 QH105_23    QH105_61 
   QH105_12_sh QH105_13_sh   QH105_21_sh QH105_22_sh QH105_23_sh  QH105_96_sh
   QH108_2 QH108_3 QH108_4 QH108_6 QH108_7 QH108_8    QH108_95 QH108_96
  QH114A QH114B QH114C QH114D QH114E QH114F QH114G QH114H QH114I QH114J QH114K QH115A QH115B QH115C QH115D QH115E QH115F  QH115H QH116
  QH131_11 QH131_12     QH131_33 QH131_34 QH131_35  
  QH132_11 QH132_12 QH132_13 QH132_21  QH132_23  QH132_31 QH132_32   QH132_35  
  QH133_11  QH133_13 QH133_21 QH133_22     QH133_31 QH133_32 QH133_33 QH133_34   QH133_96
   memsleep
  QH111A_1 QH111A_2 QH111A_3 QH111B_1 QH111B_2 QH111B_3
  QH111C_1 QH111C_2  QH111D_1 QH111D_2 QH111D_3
  QH111E_1 QH111E_2 QH111E_3 QH111F_1 QH111F_2 QH111F_3
  QH111G_1 QH111G_2 QH111G_3 landarea
  /missing meansub
  /analysis
  QH101_11 QH101_12 QH101_13 QH101_14 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42   QH101_71  QH101_91 QH101_96
  QH105_11 QH105_12 QH105_13   QH105_21 QH105_22 QH105_23    QH105_61 
   QH105_12_sh QH105_13_sh   QH105_21_sh QH105_22_sh QH105_23_sh  QH105_96_sh
   QH108_2 QH108_3 QH108_4 QH108_6 QH108_7 QH108_8    QH108_95 QH108_96
  QH114A QH114B QH114C QH114D QH114E QH114F QH114G QH114H QH114I QH114J QH114K QH115A QH115B QH115C QH115D QH115E QH115F  QH115H QH116
  QH131_11 QH131_12     QH131_33 QH131_34 QH131_35  
  QH132_11 QH132_12 QH132_13 QH132_21  QH132_23  QH132_31 QH132_32   QH132_35  
  QH133_11  QH133_13 QH133_21 QH133_22     QH133_31 QH133_32 QH133_33 QH133_34   QH133_96
   memsleep
  QH111A_1 QH111A_2 QH111A_3 QH111B_1 QH111B_2 QH111B_3
  QH111C_1 QH111C_2  QH111D_1 QH111D_2 QH111D_3
  QH111E_1 QH111E_2 QH111E_3 QH111F_1 QH111F_2 QH111F_3
  QH111G_1 QH111G_2 QH111G_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.

* Variables removed from rural for PCA analysis.
* QH105_13.

factor /variables
  QH101_11 QH101_12 QH101_13 QH101_14 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42   QH101_71 QH101_81 QH101_91 QH101_96
  QH105_11 QH105_12 QH105_21 QH105_22 QH105_23 QH105_31   QH105_61 QH105_96
   QH105_12_sh QH105_13_sh   QH105_21_sh QH105_22_sh QH105_23_sh QH105_31_sh   QH105_96_sh
   QH108_2 QH108_3 QH108_4 QH108_6 QH108_7 QH108_8 QH108_9 QH108_10 QH108_11 QH108_95 QH108_96
  QH114A QH114B QH114C QH114D QH114E QH114F QH114G QH114H QH114I QH114J QH114K QH115A QH115B QH115C QH115D QH115E QH115F  QH115H QH116
  QH131_11 QH131_12     QH131_33 QH131_34 QH131_35  
  QH132_11 QH132_12 QH132_13 QH132_21  QH132_23  QH132_31 QH132_32   QH132_35  
  QH133_11 QH133_12 QH133_13 QH133_21 QH133_22     QH133_31 QH133_32 QH133_33 QH133_34   QH133_96
   memsleep
  QH111A_1 QH111A_2 QH111A_3 QH111B_1 QH111B_2 QH111B_3
  QH111C_1 QH111C_2 QH111C_3 QH111D_1 QH111D_2 QH111D_3
  QH111E_1 QH111E_2 QH111E_3 QH111F_1 QH111F_2 QH111F_3
  QH111G_1 QH111G_2 QH111G_3 landarea
  /missing meansub
  /analysis
  QH101_11 QH101_12 QH101_13 QH101_14 QH101_21 QH101_31 QH101_32 QH101_41 QH101_42   QH101_71 QH101_81 QH101_91 QH101_96
  QH105_11 QH105_12 QH105_21 QH105_22 QH105_23 QH105_31   QH105_61 QH105_96
   QH105_12_sh QH105_13_sh   QH105_21_sh QH105_22_sh QH105_23_sh QH105_31_sh   QH105_96_sh
   QH108_2 QH108_3 QH108_4 QH108_6 QH108_7 QH108_8 QH108_9 QH108_10 QH108_11 QH108_95 QH108_96
  QH114A QH114B QH114C QH114D QH114E QH114F QH114G QH114H QH114I QH114J QH114K QH115A QH115B QH115C QH115D QH115E QH115F  QH115H QH116
  QH131_11 QH131_12 QH131_33 QH131_34 QH131_35  
  QH132_11 QH132_12 QH132_13 QH132_21  QH132_23  QH132_31 QH132_32   QH132_35  
  QH133_11 QH133_12 QH133_13 QH133_21 QH133_22     QH133_31 QH133_32 QH133_33 QH133_34   QH133_96
   memsleep
  QH111A_1 QH111A_2 QH111A_3 QH111B_1 QH111B_2 QH111B_3
  QH111C_1 QH111C_2 QH111C_3 QH111D_1 QH111D_2 QH111D_3
  QH111E_1 QH111E_2 QH111E_3 QH111F_1 QH111F_2 QH111F_3
  QH111G_1 QH111G_2 QH111G_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 7/30/2018 - 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_71+QH101_81+QH101_91+QH101_96+
  QH105_11+QH105_12+QH105_13+QH105_21+QH105_22+QH105_23+QH105_31+QH105_61+QH105_96+
  QH105_12_sh+QH105_13_sh+QH105_21_sh+QH105_22_sh+QH105_23_sh+QH105_31_sh+QH105_96_sh+
  QH108_2+QH108_3+QH108_4+QH108_6+QH108_7+QH108_8+QH108_9+QH108_10+QH108_11+QH108_95+QH108_96+
  QH114A+QH114B+QH114C+QH114D+QH114E+QH114F+QH114G+QH114H+QH114I+QH114J+QH114K+QH115A+QH115B+QH115C+QH115D+QH115E+QH115F+QH115H+QH116+
  QH131_11+QH131_12+QH131_33+QH131_34+QH131_35+
  QH132_11+QH132_12+QH132_13+QH132_21+QH132_23+QH132_31+QH132_32+QH132_35+
  QH133_11+QH133_12+QH133_13+QH133_21+QH133_22+QH133_31+QH133_32+QH133_33+QH133_34+QH133_96+
  memsleep+
  QH111A_1+QH111A_2+QH111A_3+QH111B_1+QH111B_2+QH111B_3+
  QH111C_1+QH111C_2+QH111C_3+QH111D_1+QH111D_2+QH111D_3+
  QH111E_1+QH111E_2+QH111E_3+QH111F_1+QH111F_2+QH111F_3+
  QH111G_1+QH111G_2+QH111G_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_71 QH101_81 QH101_91 QH101_96
  QH105_11 QH105_12 QH105_13   QH105_21 QH105_22 QH105_23 QH105_31   QH105_61 QH105_96
   QH105_12_sh QH105_13_sh   QH105_21_sh QH105_22_sh QH105_23_sh QH105_31_sh   QH105_96_sh
   QH108_2 QH108_3 QH108_4  QH108_6 QH108_7 QH108_8 QH108_9 QH108_10 QH108_11 QH108_95 QH108_96
  QH114A QH114B QH114C QH114D QH114E QH114F QH114G QH114H QH114I QH114J QH114K QH115A QH115B QH115C QH115D QH115E QH115F  QH115H QH116
  QH131_11 QH131_12     QH131_33 QH131_34 QH131_35  
  QH132_11 QH132_12 QH132_13 QH132_21  QH132_23  QH132_31 QH132_32   QH132_35  
  QH133_11 QH133_12 QH133_13 QH133_21 QH133_22     QH133_31 QH133_32 QH133_33 QH133_34   QH133_96
   memsleep
  QH111A_1 QH111A_2 QH111A_3 QH111B_1 QH111B_2 QH111B_3
  QH111C_1 QH111C_2 QH111C_3 QH111D_1 QH111D_2 QH111D_3
  QH111E_1 QH111E_2 QH111E_3 QH111F_1 QH111F_2 QH111F_3
  QH111G_1 QH111G_2 QH111G_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 QHCONCES 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, Burkina Faso MIS 2017-18'
  corner='Residence/region' /slabels visible=no.