Search found 135 matches
- Thu Aug 18, 2022 3:17 am
- Forum: Add-in Support
- Topic: aim_solve (DSGE model simulation)
- Replies: 18
- Views: 46051
Re: aim_solve (DSGE model simulation)
Returning to this after nine years... There seems to be a "Catch 22" with this add-in. If I use R 4.2.1, I get the error message: "Package 'AMA' was built before R 3.0.0: please re-install it" But if I use R 2.15.3, I get the error message: "Failed to initialize EViewsRConn....
- Fri May 09, 2014 8:36 am
- Forum: Suggestions and Requests
- Topic: Proc/Make Graph in Model (EViews 8)
- Replies: 2
- Views: 5610
Re: Proc/Make Graph in Model (EViews 8)
Thanks very much for your reply, Chris. 1. Sample: I take your point, but I still think it would be more "natural" for the graphs just to default to the "Sample (adjusted): " shown in the Model after solving. Your aproach would require an adjustment each time that "Sample (a...
- Thu May 08, 2014 9:51 am
- Forum: Suggestions and Requests
- Topic: Proc/Make Graph in Model (EViews 8)
- Replies: 2
- Views: 5610
Proc/Make Graph in Model (EViews 8)
When using "Proc/Make Graph" in a Model, the "Sample for Graph" defaults to the entire range of the Workfile. Since most models do not solve over the whole range, it would be nice if the default were to be the range over which the model was solved. This would avoid strange-lookin...
- Tue Feb 12, 2013 7:29 am
- Forum: Suggestions and Requests
- Topic: "View Unread Posts"
- Replies: 0
- Views: 3766
"View Unread Posts"
Hello,
Is there any particular reason why there is no "View Unread Posts" section in the Forum (as, for example, in the RATS or Dynare fora)?
If not, it would be helpful to have one.
Regards
Donihue
Is there any particular reason why there is no "View Unread Posts" section in the Forum (as, for example, in the RATS or Dynare fora)?
If not, it would be helpful to have one.
Regards
Donihue
- Tue Jan 24, 2012 2:32 am
- Forum: Suggestions and Requests
- Topic: Graphs comparing actuals and model scenarios
- Replies: 0
- Views: 3021
Graphs comparing actuals and model scenarios
When a model's solution sample is shorter than the graph sample, the actuals prior/posterior to the solution sample appear in the graph (generated by Proc/Make Graph) in the same colour as the solution values; it would be nice if they could instead appear in the same colour as the other actuals. Reg...
- Tue Jan 24, 2012 1:38 am
- Forum: Econometric Discussions
- Topic: Auto regressive distributed lagged models.
- Replies: 2
- Views: 6760
Re: Auto regressive distributed lagged models.
For equation 1, it is really very easy to estimate the equations by introducing the various lagged variables. The hard part is in determining the number of lags. There is no "formulaic" answer to that. The "general to specific" approach of the LSE school suggests starting with a ...
- Tue Dec 27, 2011 11:15 pm
- Forum: Econometric Discussions
- Topic: Johansen cointegration
- Replies: 11
- Views: 14707
Re: Johansen cointegration
You can run the test, but only after transforming the I(2) variable into an I(1) variable by first-differencing it
Regards
Donihue
Regards
Donihue
- Tue Dec 27, 2011 11:10 pm
- Forum: Econometric Discussions
- Topic: VECM - Interpretation of Estimates
- Replies: 5
- Views: 20596
Re: VECM - Interpretation of Estimates
In principle, the speed of adjustment parameters α(y) (the coefficients on "cointeq1") should be negative and lie between (0, -1). This is because in a VEC model, the point estimate should imply that y(t) converges to the long-run equilibrium relationship – if y is above its long-term valu...
- Thu Dec 22, 2011 12:55 am
- Forum: Bug Reports
- Topic: alias in solve
- Replies: 2
- Views: 4293
Re: alias in solve
I just ran Gareth's test programme on my copy of EViews 7.2, build 29 Nov 2011 and received the following error message in the Programme Log:
Illegal scenario alias _TEST1 in "DO_ M.SCENARIO(A=TEST1) TEST".
Regards
Donihue
Illegal scenario alias _TEST1 in "DO_ M.SCENARIO(A=TEST1) TEST".
Regards
Donihue
- Mon Dec 05, 2011 1:59 pm
- Forum: Programming
- Topic: Creating an equation from strings
- Replies: 2
- Views: 3823
Re: Creating an equation from strings
Thanks very much, Gareth, for catching those silly errors. Also, I had not realised that I needed to use the "@str" syntax. I have corrected and it runs pefectly now.
Regards
Donihue
Regards
Donihue
- Mon Dec 05, 2011 12:01 pm
- Forum: Programming
- Topic: Creating an equation from strings
- Replies: 2
- Views: 3823
Creating an equation from strings
Hello, I would like to create a simulation model from equations generated using matrices of coefficients obtained from Matlab through xget, but am unsure of the syntax to use. I naively tried the following ' create model from dr.ghx and dr.ghu model mod1 %eq = " " %eq = %eq + "+"...
- Wed Nov 30, 2011 5:02 pm
- Forum: Add-in Support
- Topic: Broken BVAR??
- Replies: 5
- Views: 8037
Re: Broken BVAR??
Thanks. I understand then that the index limit is 750.
Regards
Donihue
Regards
Donihue
- Wed Nov 30, 2011 2:32 pm
- Forum: Add-in Support
- Topic: Broken BVAR??
- Replies: 5
- Views: 8037
Re: Broken BVAR??
I repeated the installation of the new EViews 7.2 29 Nov 2011 build and the 27/07/2011 bvar programme, with the same (negative) results. However, when I then manually pointed the add-in to the new bvar programme (by double-clicking on it in the "manage add-ins" window) it worked... An unre...
- Wed Nov 30, 2011 2:21 pm
- Forum: Add-in Support
- Topic: Broken BVAR??
- Replies: 5
- Views: 8037
Re: Broken BVAR??
Strange ...
I will try reinstalling everything to see if it is a problem with my installation.
Regards
Donihue
I will try reinstalling everything to see if it is a problem with my installation.
Regards
Donihue
- Wed Nov 30, 2011 1:48 pm
- Forum: Add-in Support
- Topic: Broken BVAR??
- Replies: 5
- Views: 8037
Broken BVAR??
When I use the latest EViews 7.2 build (Nov 29 2011) with the (excellent) BVAR add-in in what I assume is its latest version (downloaded 30 Nov 2011, but the "bvar" programme is dated 27/07/2011), nothing happens: no "bvar" spool is produced. By contrast, if I use the "bvar&...