Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "Daniel Ilg" <daniel.ilg@ku.de> |
To | <statalist@hsphsun2.harvard.edu> |
Subject | RE: st: VECM: Deterministic Factors & Significance for ce1 in short-run parameters |
Date | Thu, 7 Feb 2013 17:15:46 +0100 |
Dear Prakash, Thank you for your answer! I thought, a cointegration relation proven through Johannsen or 2-Step-Eagle-Granger-Approach (or other tests of the residuals) is sufficient. Am I wrong? I read as well that the cointegrating coefficient should be negative and between 0 and 1. Do you have a clue why? Best regards, Daniel Mit freundlichen Grüßen/Best regards Daniel Ilg wissenschaftlicher Mitarbeiter/Research Associate Lehrstuhl für Wirtschaftstheorie/Chair of Economic Theory Katholische Universität Eichstätt-Ingolstadt/Catholic University Eichstaett-Ingolstadt Auf der Schanz 49 85049 Ingolstadt Tel.: +49 841 937 1857 Mobil: +49 171 653 113 1 E-Mail: daniel.ilg@ku.de -----Original Message----- From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Prakash Singh Sent: Thursday, February 07, 2013 4:58 PM To: statalist@hsphsun2.harvard.edu Subject: Re: st: VECM: Deterministic Factors & Significance for ce1 in short-run parameters Dear Daniel As far as my knowledge goes significant ce term is essential for cointegration; in other words significant ce terms indicate presence of cointegration and the size of cointegrating coefficient is supposed to be negative and should be in between 0 to 1. Hope it helps Prakash On Wed, Feb 6, 2013 at 7:04 PM, Daniel Ilg <daniel.ilg@ku.de> wrote: > Dear users, > > I have 1 problem and 1 question. > I apply the VECM for a time series. My dependent variable is default > probability and all variables are I(1). > > My problem: > I want to determine the deterministic components for my VECM. > My independent variables have different deterministic components, so I > can't derive my deterministic factors from theory. Another problem is, > that I'm just interested in a cointegration relation of 1 (default > probability is the variable I want to explain). So I'm not interested > in more ranks than 1. I applied pentula and modified pentula principle > but the problem is, I get more ranks and - as said before - I'm just > interested in 1 cointegration relation. So, how can I determine the > deterministic components of my VECM for rank = 1? > > My question: > When I get my VEC output does my "ce1" need to be significant in my > Error Correction "d_default_probability"? What does it mean when "ce1" > is not significant in the short-run? > > Thx a lot & regards, > Daniel > > > * > * 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/ * * 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/ * * 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/