Search found 6 matches
- Thu Dec 22, 2011 6:56 pm
- Forum: Econometric Discussions
- Topic: Lag length Selection and Including Trend or not
- Replies: 0
- Views: 2177
Lag length Selection and Including Trend or not
Hi, I just wanted some clarification on two issues. (1) When we are running unit root tests on panel data (suppose IPS or LLC unit root test), we need to enter the lag length; in case we decide not to go by the automatic lag selection by AIC or SIC. How should we select the user-defined lag length f...
- Sun Aug 07, 2011 4:20 pm
- Forum: Econometric Discussions
- Topic: Can I run Cointegration test with I(1,2)?
- Replies: 1
- Views: 2829
Re: Can I run Cointegration test with I(1,2)?
Yes, you may test for cointegration.
- Sun Aug 07, 2011 4:18 pm
- Forum: Econometric Discussions
- Topic: Cointegration
- Replies: 1
- Views: 3314
Re: Cointegration
You can not run the Johansen cointegration test for I(0) series. They have to be I(1).
- Sun Aug 07, 2011 4:16 pm
- Forum: Econometric Discussions
- Topic: General Cointegration Question
- Replies: 1
- Views: 2882
Re: General Cointegration Question
If there is a unit root present in your series at level, this means that the series are not integrated of order I(0). When first differenced, there is no unit root present, it means that your series are now stationary and of order I(1). Since, both series are of same order, there is a chance of coin...
- Sun Aug 07, 2011 10:40 am
- Forum: Estimation
- Topic: Assumption for Johansen Cointegration Test
- Replies: 2
- Views: 3847
Re: Assumption for Johansen Cointegration Test
Does this mean that we can not check Granger causality between the two variables, if they are both of the order I(0)?
- Sun Aug 07, 2011 10:03 am
- Forum: Estimation
- Topic: Assumption for Johansen Cointegration Test
- Replies: 2
- Views: 3847
Assumption for Johansen Cointegration Test
If two series are integrated of the order I(0), means there is no unit root or that they are stationary at level; can we perform Johansen Co-integration Test for them?
