Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: ts unit root test

From   Nick Cox <>
Subject   Re: st: ts unit root test
Date   Tue, 22 Feb 2011 09:27:05 +0000

One of your questions is an FAQ:

I have a certain version of Stata and have come across a user-written
program that is apparently written for a later version of Stata. What
are my options?

With this size of dataset, plotting the data to look for major
problems sounds competitive with other possibilities.


On Tue, Feb 22, 2011 at 9:19 AM, api <> wrote:

> I have a panel database with panel and time variables.
> panels are 11 countries, and times are 29 years (for each country).
> I'm trying to do a unit root test from time series menu, and im getting this
> error:
> sample may not include multiple panels
> The command im trying is: dfuller
> I tried adding an if condition, to take one panel (1 country), it say not
> enough observations
> So my questions are:
> 1- what is the command for doing panel unit root test?
> 2- i searched and there is a command :xtunitroot can do the trick, but it is
> for version 11 mine is version 10, how to use it?
> 3- xtunitroot need data to be strongly balanced, mine is weakly balanced (i
> have missing values and i guess this what made it weakly balanced).
*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index