// Creates w_hhize from the number of people in the household via hidp and pno
// INPUT FILE - w_indall.dta
// OUTPUT FILE - w_hhsize.dta

// WRITE FILEPATH WHERE YOU HAVE DOWNLOADED THE DATA
global in ""
// WRITE FILEPATH WHERE YOU WOULD LIKE TO SAVE THE OUTPUT FILE
global outpath ""

// 1 is for BHPS, 2 is for UKHLS
global cohort "2" 

foreach w in a b c d e f g h i j { // INCLUDE WAVE LETTERS FOR THE WAVES NEEDED
global wave "`w'_"
global num=strpos("abcdefghijklmnopqrstuvwxyz","`w'")
global dta ""
global waveno=$num
global inpath "${in}/bhps_w${num}"
if $cohort==2 {
	global waveno=$num+18	
	global inpath "${in}/ukhls_w${num}"
}


use "${inpath}/${wave}indall${dta}", clear

/* -------------ORIGINAL CODE-----------------*/
capture bys ${wave}hidp: gen ${wave}hhsize_dv = _N // new variable based on hidp duplicates.
lab var ${wave}hhsize_dv "Household size, based on number of hidp duplicates"

preserve
keep ${wave}hidp ${wave}pno ${wave}hhsize_dv
lab dat "Household size, all enumerated individuals"
save "${outpath}/${wave}hhsize_dv.dta", replace
restore

}