Search found 32 matches
- Sun May 20, 2018 7:46 pm
- Forum: Estimation
- Topic: Threshold Vector Autoregression
- Replies: 0
- Views: 2809
Threshold Vector Autoregression
Hi I know that Eviews has the threshold regression package, which can be used for single equation threshold autoregressions (TAR), but can it handle vectors? I have two equations which I believe to be correlated. So I'd like to estimated a TVAR. Is there an Eviews package for this? I'm aware of the ...
- Sun May 06, 2018 12:48 pm
- Forum: Estimation
- Topic: Toda and Yamamoto causality test
- Replies: 19
- Views: 29555
Re: Toda and Yamamoto causality test
sam SAM wrote:I do not know where the problem is (at home)!!!
Looking to help out as I know how frustrating it can be. But I don't understand your comment. You mean you can't find the instructions?
- Sun May 06, 2018 12:46 pm
- Forum: Estimation
- Topic: Toda and Yamamoto causality test
- Replies: 19
- Views: 29555
Re: Toda and Yamamoto causality test
Hello thank you very much I feel that the site is not updated? Cordially I don't understand why you would need the blog post to be updated. The method has not changed since year 1995. The blog lays out very clear instructions on how to step by step implement the T-Y method. You don't even need to p...
- Sun May 06, 2018 9:06 am
- Forum: Estimation
- Topic: Toda and Yamamoto causality test
- Replies: 19
- Views: 29555
Re: Toda and Yamamoto causality test
Good Morning, Hello, Please, It's true this remark: Toda-Yammamoto procedure requires that the maximum order of integration among the variables should not exceed the lags of the initial VAR? Best wishes There is a great blog post that explains the T-Y approach very clearly. Search Dave Giles profes...
- Tue Mar 28, 2017 10:17 am
- Forum: Programming
- Topic: How can I quickly create weekly dummy variables?
- Replies: 2
- Views: 3119
Re: How can I quickly create weekly dummy variables?
EViews Gareth wrote:@expand(@datepart(@date, "WW"), @dropfirst)
This works very well. Thank you!
- Tue Mar 28, 2017 10:06 am
- Forum: Programming
- Topic: How can I quickly create weekly dummy variables?
- Replies: 2
- Views: 3119
How can I quickly create weekly dummy variables?
Hi,
I have weekly data and I'm interesting in introducing weekly dummies to examine for seasonality. I tried using @expand(@week, @dropfirst) but I get an error message. Is there some other way to do this?
I have weekly data and I'm interesting in introducing weekly dummies to examine for seasonality. I tried using @expand(@week, @dropfirst) but I get an error message. Is there some other way to do this?
- Tue Mar 28, 2017 10:03 am
- Forum: Add-in Support
- Topic: STAR*
- Replies: 52
- Views: 107893
Re: STAR*
Hi, I am getting an error message these days when I try to run the STAR package. This just recently started. I cannot figure out why this problem is occurring, as the package was working fine just yesterday. Hi, It is because the LM_1 statistical is negative, It has never happened to me. Could you ...
- Sun Mar 12, 2017 11:03 am
- Forum: Programming
- Topic: Generating Random Starting Values
- Replies: 1
- Views: 2495
Generating Random Starting Values
Hi I'm trying to randomly generate 16 starting values for a nonlinear MRSTAR. I understand that starting values can be specified by the following: param c(1) scalar c(2) scalar c(3) scalar c(4) scalar c(5) scalar c(6) scalar c(7) scalar c(8) scalar c(9) scalar c(10) scalar c(11) scalar c(12) scalar ...
- Fri Mar 10, 2017 9:51 am
- Forum: Add-in Support
- Topic: STAR*
- Replies: 52
- Views: 107893
Re: STAR*
Hi,
I am getting an error message these days when I try to run the STAR package. This just recently started. I cannot figure out why this problem is occurring, as the package was working fine just yesterday.
I am getting an error message these days when I try to run the STAR package. This just recently started. I cannot figure out why this problem is occurring, as the package was working fine just yesterday.
- Wed Mar 08, 2017 2:38 pm
- Forum: Programming
- Topic: Squared difference of each element in a vector
- Replies: 2
- Views: 3764
Re: Squared difference of each element in a vector
Thank you Matt!
- Wed Mar 08, 2017 9:52 am
- Forum: Programming
- Topic: Squared difference of each element in a vector
- Replies: 2
- Views: 3764
Squared difference of each element in a vector
Hi I'm sorry this is such a basic question, but I cannot find the answer in Eviews help forum. I have a 1x10 vector of eigenvalues and I have a scalar mean of those eigenvalues. For each element of the vector, I'd like to subtract the mean, square the difference and sum the squared differences. In M...
- Tue Jul 26, 2016 3:29 am
- Forum: Econometric Discussions
- Topic: Negative LM statistic in testing for autocorrelation
- Replies: 0
- Views: 2316
Negative LM statistic in testing for autocorrelation
I am attempting some testing of adequacy in the post estimation of a STAR model. Specifically I'm attempting to test for the presence of no autocorrelation using the methods of Eitrheim and Terasvirta (1996). This is a Serial Correlation LM test which is Chi-squared distributed. Summary of methods f...
- Mon Jul 25, 2016 7:57 pm
- Forum: Add-in Support
- Topic: STAR*
- Replies: 52
- Views: 107893
Re: STAR*
Dear Nicolas, I am attempting some testing of adequacy in the post estimation of my STAR model. Specifically I'm attempting to test for the presence of no autocorrelation using the methods of Eitrheim and Terasvirta (1996). This is a Serial Correlation LM test which is Chi-squared distributed. Howev...
- Wed May 25, 2016 10:59 am
- Forum: Programming
- Topic: generate a vector of random values
- Replies: 3
- Views: 4437
Re: generate a vector of random values
EViews Glenn wrote:@rnorm works best for element assignment. To fill the entire vector in one go, useCode: Select all
nrnd(vec)
as inCode: Select all
vector(10) a
nrnd(a)
Thank you this is very efficient in my program!
- Tue May 24, 2016 5:24 pm
- Forum: Add-in Support
- Topic: STAR*
- Replies: 52
- Views: 107893
Re: STAR*
The final test that one should always do is to compare the linear model with the nonlinear in terms of adjustment, if the nonlinear one gives you better results you should keep it. Regarding the stationarity of the transition variable, since you apply a funcion which codomine is bounded the resulti...