Identifying admissions 2 days either side of an event

[Minda Sarna]

Hello,
I have Dataset A where an event occurred. I have a tag for the event and an event date. In Dataset B, I would like to identify all the admissions two days either side of this event. So if the event occurred on the 5th of June, I would like to tag admissions from the 3rd of June to the 7th of June. Could you please help with how I might code this? thank you, Minda

[Ken Chui]

Try rangejoin. Here is a similar Q&A on StackOverflow: https://stackoverflow.com/questions/...range-of-dates

[Jared Greathouse]

Consider a panel dataset where we have one unit that is treated.

u "http://econ.korea.ac.kr/~chirokhan/panelbook/data/basque-clean.dta", clear

loc int_time = 1975

g treated = cond(regionno==17 & year >= `int_time',1,0)

labvars year gdpcap "Year" "ln(GDP per 100,000)"


// I use labvars, but you don't need it.

replace regionname = trim(regexr(regionname,"\(.+\) *",""))

egen id = group(regionname), label(regionname) // makes a unique ID

order id, b(year)

*keep if year >= 1960
drop if inlist(id,18) //12

drop regionno
xtset id year, y


loc time: disp "`r(timevar)'"

g rel = `time'-`int_time'

keep if inrange(rel,-5,5)

This is a panel dataset of 17 Spanish communities, where a unit was treated in 1975. To calculate event time, you simply subtract the time variable from the date of the first intervention.

You don't give your datasets, so I can't comment on them, but it's likely a matter of merging the treatment variable/units to the dates you have for treatment, and following the code I've given here to suit your purposes.