set logtype text
log using e:\DHS\programs\tests\diffs_between_surveys_log_22July2016.txt, replace

* Tom Pullum, tom.pullum@icfi.com, July 25, 2016

set more off
cd e:\DHS\DHS_data\KR_files

****************************************************************

program define setup1

* Construct the indicator, number the surveys, save the needed variables

scalar ssurvey=ssurvey+1
local lsurvey=ssurvey
gen survey=ssurvey

* CONSTRUCT THE INDICATOR

* values other than 0 and 1 should be interpreted as .
replace g100=. if g100>1
replace g102=. if g102>1

gen y = .
replace y=0 if g100<.
replace y=1 if g102==1  

keep v005 v021 v023 y survey
save temp_`lsurvey'.dta, replace

end

****************************************************************

program define setup2

* Combine the surveys into one file

use temp_1.dta, clear
append using temp_2.dta

egen cluster=group(v021 survey) 
egen stratum=group(v023 survey) 

save temp.dta, replace

end

****************************************************************

program define analyze

* Test whether the "survey" variable is statistically significant

svyset cluster [pweight=v005], strata(stratum) singleunit(scaled)

tab survey y
tab survey y [iweight=v005/1000000], row

* Test for significance of change or difference
svy: logit y i.survey
scalar p=e(p)
scalar list p

* p is the significance of a test of H0: in the population, there was no difference 
*  in the prevalence of the outcome across the surveys

end

****************************************************************
****************************************************************
****************************************************************
****************************************************************
****************************************************************
* EXECUTION BEGINS HERE

* Example:  difference between two surveys in FGM prevalence

* Kenya 27.1% in 2008-09 vs 21.0% in 2014

scalar ssurvey=0

use e:\DHS\DHS_data\IR_files\KEIR52FL.dta, clear 
setup1

use e:\DHS\DHS_data\IR_files\KEIR70FL.dta, clear 
setup1

setup2
analyze