Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re: Stata Helpp File 'Levinlin'

From   Christopher F Baum <[email protected]>
To   "Tonini, Axel" <[email protected]>
Subject   st: Re: Stata Helpp File 'Levinlin'
Date   Fri, 13 Aug 2004 09:14:30 -0400

Dear Axel

The test is applied to the variable specified in the command. As a convenience, and like many other Stata commands, levinlin allows time-series operators to be used in this variable. Just as one might test the (log) money supply for a unit root, and then test the difference of that variable for a unit root (to determine whether money is I(0), I(1) or I(2)) levinlin could be applied to a series which is itself, e.g., a growth rate rather than a (log) level. Then one is asking whether GDP growth rates are stationary or not. But the test proposed by Levin, Lin, Chu will be applied to whatever variable you specify.

Best wishes
Kit Baum

On Aug 13, 2004, at 9:09 AM, Tonini, Axel wrote:

Dear Dr. Baum,

I saw that in the Help file for the �levinlin� test in STATA allow the possibility of the �D.� command for first difference in the variable.

This confuses me a bit, in a sense that equation (1) in the Levin�s article (2002) considers on the left hand side the dependent variable already in first difference.

So in order to perform the test as stated in equation (1) I have to add the command �D.� ?

I would kindly appreciate your suggestion interpreting the additional possibility of the command �D. � in the help file of the levinlin program (this concerns other tests for convergence available in STATA).

Thank you in advance.

Best regards,

Axel Tonini


Axel Tonini
PhD student
Agricultural Economics and Rural Policy Group - BODE 16
Department of Social Sciences-Wageningen University
Temporary address (to August 2005): Mansholtlaan 10-12, 6708 PA Wageningen (Building 127, Room A435)
Mail address: P.O. Box 9130, NL- 6700 EW Wageningen ����������
The Netherlands
Tel.: +31 (0) 317 482949
Fax:� +31 (0) 317 484736
E-mail:�� [email protected]
Aan dit bericht kunnen geen rechten worden ontleend.
Het bericht is alleen bestemd voor de geadresseerde.
Indien dit bericht niet voor u is bestemd, verzoeken wij u dit onmiddellijk aan ons te melden en de inhoud van het bericht te vernietigen.
This message shall not constitute any obligations.
This message is intended solely for the addressee.
If you have received this message in error, please inform us immediately and delete its contents.

© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index