There may be a better way, but this appears to work.
You have evidently -tsset- the data.
What we can do is count downwards by subtracting one
from the previous length. A spell of length 3 means
that the values will go down 3, 2, 1. When we
drop below 1 the spell has ended.
As there is no value before the first, that needs
to be trapped as a special case.
gen ongoing = length
replace ongoing = L.ongoing - 1 if length == 0 & L.ongoing < .
replace ongoing = ongoing >= 1
Nick
[email protected]
Drury, A. Cooper
> I am working with a times-series cross-section data set where the unit
> of analysis is the country-pair/year. The data include a dichotomous
> variable indicated when a new policy was initiated. I also have a
> variable that indicates of the duration of that policy (measured in
> years). I need to create a variable that indicates when the
> policy was
> in effect. For example, one cross-section my look like this:
>
> Policy Policy Policy
> Initiation length ongoing (new variable)
> 0 0 0
> 1 3 1
> 0 0 1
> 0 0 1
> 0 0 0
> 1 2 1
> 0 0 1
> 0 0 0
>
> I need to create the "policy ongoing" variable.
>
> I have tried generating a new variable, and then typing:
> replace newvariable=L.newvariable+(policylength-1)+policyinitiation
>
> This should work, but Stata tells me: (593368 real changes
> made, 593368
> to missing); so all the values are replaced by missing values.
>
> I am really stumped here, any help would be greatly appreciate.
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
