* Program to calculate the proportion of children in the NFHS5 KR file
*  who survived to the date of the survey, in districts in Uttar Pradesh

* Specify a workspace
cd e:\DHS\DHS_data\scratch

* Open the KR file; children born in the past 5 years
use "C:\Users\26216\ICF\Analysis - Shared Resources\Data\DHSdata\IAKR7EFL.DTA", clear 

describe v024

* The label for v024 is V024; list it
label list V024

* Uttar Pradesh is v024=9 
keep if v024==9

* How many districts are in Uttar Pradesh?
codebook sdist

* 75 districts

svyset v001 [pweight=v005], strata(v023) singleunit(centered)
svy: proportion b5, over(sdist)

* the lines with the output "0" give the proportion of children who died, with a confidence interval

* Save the results and copy into Excel

matrix S=r(table)
matrix T=S'

* construct a file with the district names and n's, weighted and unweighted
gen unwtdn=1
gen wtdn=sweight/1000000

collapse (sum) *wtdn,by(sdist)
rename sdist district
label values district SDIST
label variable unwtdn "N (unweighted)"
label variable wtdn "N (weighted)"
gen line=_n
sort line
save stub.dta, replace

clear
svmat T
matrix list T
rename T1 b
rename T2 se
rename T3 t
rename T4 pvalue
rename T5 ll
rename T6 ul
rename T7 df
rename T8 crit
rename T9 eform
gen line=_n
keep if line<=75
sort line
merge line using stub.dta
tab _merge

rename b P
rename ll L
rename ul U
label variable P "Proportion dead"
label variable L "Low end, 95% c.i."
label variable U "Upper end, 95% c.i."
keep  district P L U *wtdn
order district P L U *wtdn

list, table clean
export excel using child_survival_by_district.xlsx, replace firstrow(var)