Statalist The Stata Listserver

[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: Re: Help Creating a Lagged Variable

From   "Angeli Kirk" <>
Subject   Re: st: Re: Help Creating a Lagged Variable
Date   Tue, 12 Sep 2006 16:12:51 -0400

Do you have more than one regime change for any country?

If not, you might try:

gen regimeyear_temp= year*regimechange    [will = 0 if no change that
year or the year if there is a change]
egen regimeyear=max(regimeyear_temp), by(country)
replace regimeyear=1945 if regimeyear==0   [catches all those with no change]

This would also work if you had multiple changes but only needed to
mark year of the last regime change.


On 9/12/06, Michael Blasnik <> wrote:
This may work:

by country: gen regimeyear=year if _n==1 | regimechange==1
by country: replace regimeyear=regimeyear[_n-1] if regimeyear==.

M Blasnik

----- Original Message -----
From: "Michael Horowitz" <>
To: <>
Sent: Tuesday, September 12, 2006 2:42 PM
Subject: st: Help Creating a Lagged Variable

> To whom it may concern:
> I have data set up in country-year format, where there is one observation
> per country per year.  There is also a regime change variable that is a 0
> if no regime change occurred in that year and a 1 otherwise.  The dataset
> runs from 1945-2002.
> I am interested in creating a lagged variable for each country for each
> year that will take on the value of the start year for the dataset if
> no regime change has occurred for that country since the beginning of the
> dataset and the year of the regime change if a regime change has occurred.

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2015 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index