Sustainwell merge

.gitignore

@@ -339,3 +339,7 @@ input/EUROMODoutput/current/uk_2027_std.txt
 input/InitialPopulations/current/*
 input/InitialPopulations/testing/*
 *.dta
+src/main/java/simpaths/data/startingpop/DataParser.new
+src/main/java/simpaths/data/startingpop/DataParser.old
+input/EUROMODoutput/limit/*
+input/InitialPopulations/limit/*

analysis/fertility analysis.do

@@ -0,0 +1,78 @@
+/**************************************************************************************
+*
+*	PROGRAM TO ANALYSE EMPLOYMENT TRANSATIONS
+*
+*	Last version:  Justin van de Ven, 06 May 2025
+*	First version: Justin van de Ven, 06 May 2025
+*
+**************************************************************************************/
+
+clear all
+global moddir = "C:\Justin\dev\CeMPASimPaths\output\20251029155614\csv"
+global outdir = "C:\Justin\analysis\data\"
+cd "$outdir"
+
+
+/**************************************************************************************
+*	start
+**************************************************************************************/
+global year_start = 2015
+global year_end = 2026
+
+
+/**************************************************************************************
+*	load data
+**************************************************************************************/
+import delimited using "$moddir/BenefitUnit.csv", clear
+rename *, l
+rename id_benefitunit idbenefitunit
+gsort idbenefitunit time
+save "$outdir/temp0", replace
+import delimited using "$moddir/Person.csv", clear
+rename *, l
+rename id_person idperson
+rename socialcareprovision socialcareprovision_p
+gsort idbenefitunit time idperson
+merge m:1 idbenefitunit time using temp0
+gsort time idbenefitunit idperson
+gen refbenefitunit = 0
+replace refbenefitunit = 1 if (idbenefitunit != idbenefitunit[_n-1])
+
+destring hoursworkedweekly, replace force
+recode hoursworkedweekly (missing=0)
+gen idNotEmployedAdult = (hoursworkedweekly<0.1 & dag>17)
+
+gen led = (deh_c3=="Low")
+gen med = (deh_c3=="Medium")
+gen hed = (deh_c3=="High")
+
+gen male = (dgn=="Male")
+
+gen idbaby = (dag==0)
+bys time idbenefitunit: egen baby = sum(idbaby)
+
+save "$outdir/temp1", replace
+
+
+/**************************************************************************************
+*	analysis
+**************************************************************************************/
+use "$outdir/temp1", clear
+global year_ref = $year_start-1
+
+// block 1 statistics
+gen emp = (hoursworkedweekly>0.5)
+gen emp_to_nemp = 0
+gen nemp_to_emp = 0
+gsort idperson time
+replace emp_to_nemp = 1 if (idperson[_n-1]==idperson & time[_n-1]+1==time & emp[_n-1]==1 & emp==0)
+replace nemp_to_emp = 1 if (idperson[_n-1]==idperson & time[_n-1]+1==time & emp[_n-1]==0 & emp==1)
+order time idperson hoursworkedweekly emp emp_to_nemp
+matrix store1 = J($year_end-$year_ref,1,.)
+forvalues yy = $year_start/$year_end {
+	qui{
+		sum baby if (time==`yy' & dag>17 & dag<65), mean
+		mat store1[`yy'-${year_ref},1] = r(mean)
+	}
+}
+matlist store1

input/InitialPopulations/compile/00_master.do

@@ -56,7 +56,7 @@ global dir_ukhls_data "D:\Dasha\UK-original-data\USoc\UKDA-6614-stata\stata\stat
 *global dir_ukhls_data "C:\Users\Patryk\Documents\SP_prep_pop\ukhls\UKDA-6614-stata\stata\stata13_se\ukhls"
 
 * Directory which contains WAS data
-*global dir_was_data "J:\01 DATA\UK\was\wave7\stata\stata13_se"
+*global dir_was_data "J:\01 DATA\UK\was\wave8\stata\stata13_se"
 global dir_was_data "D:\Dasha\UK-original-data\WAS\UKDA-7215-stata\stata\stata13_se"
 *global dir_was_data "C:\Users\Patryk\Documents\WAS\UKDA-7215-stata\stata\stata13_se"
 

input/InitialPopulations/compile/02_create_UKHLS_variables.do

@@ -1326,6 +1326,33 @@ egen yhhnb = rowtotal(ypnb ypnbsp) if dhhtp_c4 == 1 | dhhtp_c4 == 2 //Household
 replace yhhnb = ypnb if dhhtp_c4 == 3 | dhhtp_c4 == 4 //If single, household income is equal to individual income
 
 
+/*Disposable income */
+sort hidp
+gen ydisp = fimnnet_dv
+recode ydisp (missing = 0)
+by hidp: egen hhinc = sum(ydisp)
+gen res = fihhmnnet1_dv - hhinc
+gen mis = (fimnnet_dv>=.)*(age_dv>17.5)
+by hidp: egen nmis = sum(mis)
+replace ydisp = res / nmis if (res>0.1 & res<. & mis==1)
+
+drop hhinc res mis nmis
+by hidp: egen hhinc = sum(ydisp)
+gen res = fihhmnnet1_dv - hhinc
+gen mis = (fimnnet_dv>=.)*(age_dv>14.5)*(age_dv<17.5)
+by hidp: egen nmis = sum(mis)
+replace ydisp = res / nmis if (res>0.1 & res<. & mis==1)
+recode ydisp (missing=0)
+/* checks 
+by hidp: egen hhinc2 = sum(ydisp)
+gen res2 = fihhmnnet1_dv - hhinc2
+gen chk = (abs(res2) > 0.1)*(fihhmnnet1_dv<.)
+order age_dv fihhmnnet1_dv fimnnet_dv ydisp hhinc res res2 mis nmis chk, a(hidp)
+tab chk
+drop hhinc2 res2 chk
+*/
+drop hhinc res mis nmis
+
 *Income CPI 
 /*CPIH INDEX 00: ALL ITEMS 2015=100
 CDID	L522
@@ -1362,6 +1389,7 @@ replace ypnb = ypnb/CPI
 replace yptc = yptc/CPI
 replace yplgrs = yplgrs/CPI
 replace ypnbsp = ypnbsp/CPI
+replace ydisp = ydisp/CPI
 
 *Inverse hyperbolic sine transformation:
 /*This transformation is useful for data that exhibit highly skewed distributions, 
@@ -1409,6 +1437,7 @@ la var ypnbihs_dv "Gross personal non-benefit income"
 la var yptciihs_dv "Gross personal non-employment, non-benefit income"
 la var yplgrs_dv "Gross personal employment income"
 la var ynbcpdf_dv "Difference between own and spouse's gross personal non-benefit income"
+la var ydisp "Disposable income (individual)"
 
 *Gross-to-net ratio  
 gen gross_net_ratio = fimngrs_dv/fimnnet_dv 
@@ -1601,7 +1630,7 @@ replace dwt = 0 if missing(dwt)
 /***************************Keep required variables***************************/
 keep ivfio idhh idperson idpartner idfather idmother dct drgn1 dwt dnc02 dnc dgn dgnsp dag dagsq dhe dhesp dcpst  ///
 	ded deh_c3 der dehsp_c3 dehm_c3 dehf_c3 dehmf_c3 dcpen dcpyy dcpex dcpagdf dlltsd dlltsd01 dlrtrd drtren dlftphm dhhtp_c4 dhm dhm_ghq dimlwt disclwt ///
-	dimxwt dhhwt jbhrs jshrs j2hrs jbstat les_c3 les_c4 lessp_c3 lessp_c4 lesdf_c4 ydses_c5 month scghq2_dv ///
+	dimxwt dhhwt jbhrs jshrs j2hrs jbstat les_c3 les_c4 lessp_c3 lessp_c4 lesdf_c4 ydses_c5 month scghq2_dv ydisp ///
 	ypnbihs_dv yptciihs_dv yplgrs_dv ynbcpdf_dv ypncp ypnoab swv sedex ssscp sprfm sedag stm dagsp lhw l1_lhw pno ppno hgbioad1 hgbioad2 der adultchildflag ///
         econ_benefits econ_benefits_nonuc econ_benefits_uc ///
 	sedcsmpl sedrsmpl scedsmpl dhh_owned dukfr dchpd dagpns dagpns_sp CPI lesnr_c2 dlltsd_sp dlltsd01_sp ypnoab_lvl *_flag  Int_Date dhe_mcs dhe_pcs dhe_mcssp dhe_pcssp dls dot dot01 unemp financial_distress

input/InitialPopulations/compile/09_finalise_input_data.do

@@ -178,26 +178,30 @@ forvalues yy = $firstSimYear/$lastSimYear {
 	//sum of weights
 	cap gen one =1
 	sum one [w=dwt]
+
+	*evaluate disposable income at household level
+	gsort idhh idbenefitunit idperson
+	by idhh idbenefitunit: egen disp_inc = sum(ydisp)
 
 	*limit saved variables
 	keep idhh idbenefitunit idperson idpartner idmother idfather pno swv dgn dag dcpst dnc02 dnc ded deh_c3 sedex jbstat les_c3 dlltsd dlltsd01 dhe ydses_c5 ///
 	yplgrs_dv ypnbihs_dv yptciihs_dv dhhtp_c4 ssscp dcpen dcpyy dcpex dcpagdf ynbcpdf_dv der sedag sprfm dagsp dehsp_c3 dhesp lessp_c3 dehm_c3 dehf_c3 ///
 	stm lesdf_c4 ppno dhm scghq2_dv dhh_owned lhw l1_lhw drgn1 dct dwt_sampling les_c4 dhm_ghq lessp_c4 adultchildflag multiplier dwt ///
 	potential_earnings_hourly l1_potential_earnings_hourly liquid_wealth tot_pen nvmhome need_socare formal_socare_hrs partner_socare_hrs daughter_socare_hrs son_socare_hrs other_socare_hrs formal_socare_cost carehoursprovidedweekly ///
         econ_benefits econ_benefits_nonuc econ_benefits_uc ///
-	ypncp ypnoab aidhrs carewho dhe_mcs dhe_pcs dhe_mcssp dhe_pcssp dls dot dot01 unemp financial_distress 
+	disp_inc ypncp ypnoab aidhrs carewho dhe_mcs dhe_pcs dhe_mcssp dhe_pcssp dls dot dot01 unemp financial_distress 
 
 	order idhh idbenefitunit idperson idpartner idmother idfather pno swv dgn dag dcpst dnc02 dnc ded deh_c3 sedex jbstat les_c3 dlltsd dlltsd01 dhe ydses_c5 yplgrs_dv ypnbihs_dv yptciihs_dv dhhtp_c4 ssscp dcpen ///
 	dcpyy dcpex dcpagdf ynbcpdf_dv der sedag sprfm dagsp dehsp_c3 dhesp lessp_c3 dehm_c3 dehf_c3 stm lesdf_c4 ppno dhm scghq2_dv dhh_owned lhw l1_lhw drgn1 dct dwt_sampling les_c4 dhm_ghq lessp_c4 adultchildflag ///
 	multiplier dwt potential_earnings_hourly l1_potential_earnings_hourly liquid_wealth tot_pen nvmhome need_socare formal_socare_hrs partner_socare_hrs daughter_socare_hrs son_socare_hrs other_socare_hrs formal_socare_cost carehoursprovidedweekly ///
         econ_benefits econ_benefits_nonuc econ_benefits_uc ///
-	ypncp ypnoab aidhrs carewho dhe_mcs dhe_pcs dhe_mcssp dhe_pcssp dls dot dot01 unemp financial_distress
+	disp_inc ypncp ypnoab aidhrs carewho dhe_mcs dhe_pcs dhe_mcssp dhe_pcssp dls dot dot01 unemp financial_distress
 
 	recode idhh idbenefitunit idperson idpartner idmother idfather pno swv dgn dag dcpst dnc02 dnc ded deh_c3 sedex jbstat les_c3 dlltsd dlltsd01 dhe ydses_c5 yplgrs_dv ypnbihs_dv yptciihs_dv dhhtp_c4 ssscp ///
 	dcpen dcpyy dcpex dcpagdf ynbcpdf_dv der sedag sprfm dagsp dehsp_c3 dhesp lessp_c3 dehm_c3 dehf_c3 stm lesdf_c4 ppno dhm scghq2_dv dhh_owned lhw l1_lhw drgn1 dct dwt_sampling les_c4 dhm_ghq lessp_c4 ///
 	adultchildflag multiplier dwt potential_earnings_hourly l1_potential_earnings_hourly liquid_wealth tot_pen nvmhome need_socare formal_socare_hrs partner_socare_hrs daughter_socare_hrs son_socare_hrs other_socare_hrs carehoursprovidedweekly ///
         econ_benefits econ_benefits_nonuc econ_benefits_uc ///
-	formal_socare_cost ypncp ypnoab aidhrs carewho dhe_mcs dhe_pcs dhe_mcssp dhe_pcssp dls dot dot01 unemp financial_distress (missing=-9)
+	formal_socare_cost disp_inc ypncp ypnoab aidhrs carewho dhe_mcs dhe_pcs dhe_mcssp dhe_pcssp dls dot dot01 unemp financial_distress (missing=-9)
 
 	gsort idhh idbenefitunit idperson
 	save "$dir_data/population_initial_UK_$year.dta", replace

input/InitialPopulations/compile/10_check_yearly_data.do

@@ -85,7 +85,8 @@ partner_socare_hrs
 daughter_socare_hrs                  
 son_socare_hrs                   
 other_socare_hrs                 
-formal_socare_cost    
+formal_socare_cost 
+disp_inc   
 ypncp                           
 ypnoab 
 dhe_mcs 
@@ -142,7 +143,8 @@ dnc
 ded
 sedex              
 dlltsd  
-dlltsd01                       
+dlltsd01   
+disp_inc                     
 ypncp                           
 ypnoab         
 yplgrs_dv                       
@@ -365,17 +367,17 @@ insheet using "$dir_data/population_initial_UK_`year'.csv", clear
 	yplgrs_dv ypnbihs_dv yptciihs_dv dhhtp_c4 ssscp dcpen dcpyy dcpex dcpagdf ynbcpdf_dv der sedag sprfm dagsp dehsp_c3 dhesp lessp_c3 dehm_c3 dehf_c3 ///
 	stm lesdf_c4 ppno dhm scghq2_dv dhh_owned lhw drgn1 dct dwt_sampling les_c4 dhm_ghq lessp_c4 adultchildflag multiplier dwt ///
 	potential_earnings_hourly l1_potential_earnings_hourly liquid_wealth need_socare formal_socare_hrs partner_socare_hrs daughter_socare_hrs son_socare_hrs other_socare_hrs formal_socare_cost ///
-	ypncp ypnoab aidhrs carewho dhe_mcs dhe_pcs dot dot01 unemp dhe_mcssp dhe_pcssp 
+	disp_inc ypncp ypnoab aidhrs carewho dhe_mcs dhe_pcs dot dot01 unemp dhe_mcssp dhe_pcssp 
 
 	order idhh idbenefitunit idperson idpartner idmother idfather pno swv dgn dag dcpst dnc02 dnc ded deh_c3 sedex jbstat les_c3 dlltsd dlltsd01 dhe ydses_c5 yplgrs_dv ypnbihs_dv yptciihs_dv dhhtp_c4 ssscp dcpen ///
 	dcpyy dcpex dcpagdf ynbcpdf_dv der sedag sprfm dagsp dehsp_c3 dhesp lessp_c3 dehm_c3 dehf_c3 stm lesdf_c4 ppno dhm scghq2_dv dhh_owned lhw drgn1 dct dwt_sampling les_c4 dhm_ghq lessp_c4 adultchildflag ///
 	multiplier dwt potential_earnings_hourly l1_potential_earnings_hourly liquid_wealth need_socare formal_socare_hrs partner_socare_hrs daughter_socare_hrs son_socare_hrs other_socare_hrs formal_socare_cost ///
-	ypncp ypnoab aidhrs carewho dhe_mcs dhe_pcs dhe_mcssp dhe_pcssp dot dot01 unemp 
+	disp_inc ypncp ypnoab aidhrs carewho dhe_mcs dhe_pcs dhe_mcssp dhe_pcssp dot dot01 unemp 
 
 	recode idhh idbenefitunit idperson idpartner idmother idfather pno swv dgn dag dcpst dnc02 dnc ded deh_c3 sedex jbstat les_c3 dlltsd dlltsd01 dhe ydses_c5 yplgrs_dv ypnbihs_dv yptciihs_dv dhhtp_c4 ssscp ///
 	dcpen dcpyy dcpex dcpagdf ynbcpdf_dv der sedag sprfm dagsp dehsp_c3 dhesp lessp_c3 dehm_c3 dehf_c3 stm lesdf_c4 ppno dhm scghq2_dv dhh_owned lhw drgn1 dct dwt_sampling les_c4 dhm_ghq lessp_c4 ///
 	adultchildflag multiplier dwt potential_earnings_hourly l1_potential_earnings_hourly liquid_wealth need_socare formal_socare_hrs partner_socare_hrs daughter_socare_hrs son_socare_hrs other_socare_hrs ///
-	formal_socare_cost ypncp ypnoab aidhrs carewho dhe_mcs dhe_pcs dhe_mcssp dhe_pcssp dot dot01 unemp  (missing=-9)
+	formal_socare_cost disp_inc ypncp ypnoab aidhrs carewho dhe_mcs dhe_pcs dhe_mcssp dhe_pcssp dot dot01 unemp  (missing=-9)
 
 	gsort idhh idbenefitunit idperson
 	save "$dir_data/population_initial_UK_`year'.dta", replace

input/InitialPopulations/compile/99_training_data.do

@@ -185,7 +185,7 @@ rename dwt2 dwt
 save "$dir_data/temp10", replace
 
 // adjust continuous variables
-foreach vv of varlist yplgrs_dv ypnbihs_dv yptciihs_dv ynbcpdf_dv liquid_wealth tot_pen nvmhome ypncp ypnoab formal_socare_hrs partner_socare_hrs daughter_socare_hrs son_socare_hrs other_socare_hrs formal_socare_cost aidhrs {
+foreach vv of varlist yplgrs_dv ypnbihs_dv yptciihs_dv ynbcpdf_dv liquid_wealth tot_pen nvmhome disp_inc ypncp ypnoab formal_socare_hrs partner_socare_hrs daughter_socare_hrs son_socare_hrs other_socare_hrs formal_socare_cost aidhrs {
 	gen tmp = `vv'
 	order tmp, a(`vv')
 	recode tmp (0=.)
@@ -212,7 +212,7 @@ save "$dir_data/temp11", replace
 
 // set benefit unit level variables
 use "$dir_data/temp11", clear
-foreach vv of varlist drgn1 ydses_c5 dhh_owned dwt liquid_wealth tot_pen nvmhome {
+foreach vv of varlist drgn1 ydses_c5 dhh_owned dwt liquid_wealth tot_pen nvmhome disp_inc {
 
 	rename `vv' `vv'i
 	bys idbenefitunit: egen `vv' = mean(`vv'i)