Re: st: Dummy variable for persistent values

[Maarten Buis <maartenlbuis@gmail.com>]

On Thu, Jul 11, 2013 at 9:33 PM, Nicole Smit wrote:
> For my bachelor thesis I am attempting to create a dummy variable as opennes
> indicator when the trade/GDP ratio of a specific country in a particular year is higher than eg. 60%. I can do this by: gen opentGDP=0
> and then: replace opentGDP=1 if tradeGDP>=60
>
> However, I would like to create a dummy for when the trade/GDP ratio is persistently higher than 60, so that actual openness of the country can be assumed instead of a random temporary increase in trade. Unfortunately I have not been able to find how I should do this.

Here is an example:

*------------------ begin example ------------------
// create some example data
clear all
set seed 123455
set obs 10 // ten countries
gen country = _n
gen openish = _n <=5 // first 5 countries are more likely to be open

expand 10 // observe each country for 10 years
bys country: gen year = _n+1999
gen trade = rbeta(10+20*openish,10)

// to make it realistic: add a missing value
replace trade = . in 17

// see what the example data looks like
sort country year
list, sepby(country)

// answer the question
gen byte miss = missing(trade)
gen byte open = trade > .6 if miss == 0
bys country miss (year) : gen byte persistent_open = sum(open)==_N if miss==0
bys country miss (year) : replace persistent_open =
persistent_open[_N] if miss == 0

// admire the result
sort country year
list, sepby(country)
*------------------- end example -------------------
* (For more on examples I sent to the Statalist see:
* http://www.maartenbuis.nl/example_faq )

Hope this helps,
Maarten

---------------------------------
Maarten L. Buis
WZB
Reichpietschufer 50
10785 Berlin
Germany

http://www.maartenbuis.nl
---------------------------------

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/