* Replicating table no. 2.19 from the India NFHS Report

* How to construct sh18c ********************

* We can get year and month of birth for
* children in the BR file, women in the IR file, men in the MR file
* Otherwise we only have hv105 to work with

* Data Preparation

* Prepare IR File
use E:\Data\NFHS-4\NFHS-4\NFHS4_74DT\IAIR74DT\IAIR74FL.DTA, clear
tab v133
tab v140
tab v140 [iweight = v005]
keep v024 v001 v002 v003 v011 v024
gen in_IR=1
rename v024 hv024
rename v001 hv001
rename v002 hv002
rename v003 hvidx
sort hv024 hv001 hv002 hvidx
save E:\Data\NFHS-4\NFHS-4\1_Calculation\IAIR74FL.DTA, replace

* Prepare MR file for merge
use E:\Data\NFHS-4\NFHS-4\NFHS4_74DT\IAMR74DT\IAMR74FL.DTA, clear
keep mv024 mv001 mv002 mv003 mv011 mv024
gen in_MR=1
rename mv024 hv024
rename mv001 hv001
rename mv002 hv002
rename mv003 hvidx
sort hv024 hv001 hv002 hvidx
save E:\Data\NFHS-4\NFHS-4\1_Calculation\IAMR74FL.DTA.dta

 * Prepare BR file for merge
use E:\Data\NFHS-4\NFHS-4\NFHS4_74DT\IABR74DT\IABR74FL.DTA, clear
keep v024 v001 v002 b16 b1 b2 b3
gen in_BR=1
rename v024 hv024
rename v001 hv001
rename v002 hv002
rename b16 hvidx
sort hv024 hv001 hv002 hvidx
save E:\Data\NFHS-4\NFHS-4\1_Calculation\IABR74FL.DTA

* Prepare PR file for merge
use E:\Data\NFHS-4\NFHS-4\NFHS4_74DT\IAPR74DT\IAPR74FL.DTA, clear
gen in_PR=1
sort hv024 hv001 hv002 hvidx
save E:\Data\NFHS-4\NFHS-4\1_Calculation\IAPR74FL.DTA, replace

***********************************************************************************
* program define merge_files

* Using PR File
use E:\Data\NFHS-4\NFHS-4\1_Calculation\IAPR74FL.DTA, clear
* Merge with BR
merge hv024 hv001 hv002 hvidx using E:\Data\NFHS-4\NFHS-4\1_Calculation\IABR74FL.DTA
rename _merge _merge_PR_BR
tab1 in_*,m
drop if in_PR==.
sort hv024 hv001 hv002 hvidx

* Merge with IR
merge hv024 hv001 hv002 hvidx using E:\Data\NFHS-4\NFHS-4\1_Calculation\IAIR74FL.DTA
rename _merge _merge_PR_IR
tab1 in_*,m
drop if in_PR==.
sort hv024 hv001 hv002 hvidx

* Merge with MR
merge hv024 hv001 hv002 hvidx using E:\Data\NFHS-4\NFHS-4\1_Calculation\IAMR74FL.DTA
rename _merge _merge_PR_MR
tab1 in_*,m
drop if in_PR==.
sort hv024 hv001 hv002 hvidx
gen cmc_of_birth=.
replace cmc_of_birth=b3    if in_BR==1
replace cmc_of_birth=v011  if in_IR==1
replace cmc_of_birth=mv011 if in_MR==1
save E:\Data\NFHS-4\NFHS-4\1_Calculation\merged_with_PR.dta

*******************************************************************************
* Calculation of new age variable (sh18c_test)
* set the scalar for the cmc of the month that is crucial for school attendance

* Checking phases: This is the section needs modification
tab shphase
* April 2014: 4+12*(2014-1900) = 1372
* April 2015: 4+12*(2015-1900) = 1384
use E:\Data\NFHS-4\NFHS-4\1_Calculation\merged_with_PR.dta, clear

* Generating different CMC for two phases
gen CMC=.
replace CMC = 4+12*(2014-1900) if shphase == 1
replace CMC = 4+12*(2015-1900) if shphase == 2
tab shphase CMC
gen must_use_hv105=0
replace must_use_hv105=1 if in_BR==. & in_IR==. & in_MR==.
gen sh18c_test=CMC-cmc_of_birth

* must remove negative values for children born AFTER CMC
replace sh18c_test=. if in_BR==1 & b3>CMC
regress sh18c_test sh18c if in_BR==1
regress sh18c_test sh18c if in_IR==1
regress sh18c_test sh18c if in_MR==1
replace sh18c_test=12*hv105-6 if must_use_hv105==1

* must remove negative values
replace sh18c_test=. if must_use_hv105==1 & sh18c_test<0
regress sh18c_test sh18c if must_use_hv105==1
regress sh18c_test sh18c if must_use_hv105==0
regress sh18c_test sh18c

* Replicate with estimated values of sh18c_test
gen sexur=hv025+2*(hv104-1)
tab hv025 hv104, summarize(sexur)
scalar L=6
scalar H=17
gen in_school=.
replace in_school=0 if hv103==1& sh18c_test>=L*12 & sh18c_test<=H*12+11
replace in_school=100 if in_school==0 & (hv121==1 | hv121==2)
tab sexur [iweight=hv005], summarize(in_school) means noobs
* Another way
tab sexur [aweight=hv005/1000000], summarize(in_school) means noobs