Search found 4 matches
- Sat May 20, 2017 12:38 pm
- Forum: Suggestions and Requests
- Topic: Suggestions: VECM do-ver
- Replies: 1
- Views: 5311
Suggestions: VECM do-ver
Hi, I'm not sure at what stage the development of Eviews 10 is but here are some suggestions re: VECM (i.e. the Cointegrated VAR). Those stem from my fairly advanced knowledge and practice of this class of models. Allow me to put in my comments along each step of the standard procedure for estimatin...
- Sat May 20, 2017 11:51 am
- Forum: Econometric Discussions
- Topic: Johansen and Granger causality test
- Replies: 1
- Views: 2517
Re: Johansen and Granger causality test
What you need to know is that cointegration implies Granger causality. However with cointegrated data in a VECM, it is difficult to interpret Granger causality as performed by Eviews . Eviews by default tests Granger causality on the first differences, excluding the error-correction term. If you are...
- Sat May 20, 2017 11:46 am
- Forum: Econometric Discussions
- Topic: VECM
- Replies: 1
- Views: 2457
Re: VECM
none of those are important. There is only one VECM --the one that fulfills all the requirements. The attractiveness of the VECM is that (1) you test for the existence of a long run relationship and (2) you extract a long run structure from the data (structure to be interpreted). Measures of fit are...
- Sat May 20, 2017 11:43 am
- Forum: Econometric Discussions
- Topic: Optimal number of dummy's in VECM?
- Replies: 1
- Views: 2467
Re: Optimal number of dummy's in VECM?
Dummies are very important for the VECM (=cointegrated VAR). Do you have 60 variables or 3 variables? If you mean "60 observations for each 3 time series" then 11 dummies is acceptable. There is no optimal number. The rule of thumb promoted by Katarina Juselius is to use a dummy (1) for ea...