Search found 1518 matches
- Wed Jun 22, 2016 5:55 am
- Forum: Econometric Discussions
- Topic: Interpreting impulse response functions: Std dev or % ?
- Replies: 21
- Views: 66824
Re: Interpreting impulse response functions: Std dev or % ?
Be careful that responses are always in the original variables and they are in whatever are the units of the variable. You cannot interpret the responses as percentage changes unless the data are put into the model in logs. In your case, response variables are log differenced, but you are interested...
- Wed Jun 22, 2016 3:47 am
- Forum: Add-in Support
- Topic: Spectral Granger Causality Test*
- Replies: 14
- Views: 51315
Re: Spectral Granger Causality Test*
I am not familiar with the methodology, but as I understand it does not have any problem with nonstationarity unlike its traditional time series counterpart. If I am not mistaken, this is one of the main advantages of working in the frequency domain. In any case, thanks for the effort and sharing.
- Wed Jun 22, 2016 3:29 am
- Forum: Econometric Discussions
- Topic: Interpreting impulse response functions: Std dev or % ?
- Replies: 21
- Views: 66824
Re: Interpreting impulse response functions: Std dev or % ?
I am sure Dakila's add-in will be a life-saver as usual. The following should clarify few points for you in the meantime: Are they directly interpretable in % terms ? Say, a 1 std variation in uncertainty has a 0.6% impact on FX (given that the variable is log-differentiated) after 4 months? Yes, th...
- Fri Jun 10, 2016 5:58 am
- Forum: Bug Reports
- Topic: Expressions are not allowed when forecasting from MIDAS
- Replies: 3
- Views: 5090
Expressions are not allowed when forecasting from MIDAS
It seems EViews is having trouble to locate the high frequency regressor if it is in an expression, when trying to forecast from an estimated MIDAS: wfcreate(page=monthly) m 2000 2015 series x = nrnd^2 pagecreate(page=quarterly) q 2000 2015 series y = nrnd equation eq.midas y c @ monthly\log(x) eq.f...
- Sat Jun 04, 2016 3:55 am
- Forum: Add-in Support
- Topic: LOCALIRFS
- Replies: 6
- Views: 22877
LOCALIRFS
This thread is about localirfs add-in for VAR-type models. It is a complementary tool for VAR object just as hdecomp and svarpatterns add-ins. The add-in allows you to produce impulse responses by local projection method introduced by Jordà (2005) and generate associated confidence bands as detailed...
- Tue May 31, 2016 12:43 am
- Forum: Econometric Discussions
- Topic: as concatenate?
- Replies: 1
- Views: 3060
Re: as concatenate?
If the result will be a numeric series, then:
Otherwise:
Code: Select all
series y = 10*y1 + y2
Otherwise:
Code: Select all
alpha y = @str(y1) + @str(y2)
- Mon May 30, 2016 4:44 am
- Forum: Estimation
- Topic: error band in the period of policy shock
- Replies: 1
- Views: 2955
Re: error band in the period of policy shock
You are correct. However, this holds if you give a shock "only" to the policy interest rate variable. By default, EViews uses Cholesky decomposition to produce the recursive error structure, which is a lower triangular matrix of impulses. When you view the impulse-responses from this facto...
- Fri May 27, 2016 7:19 am
- Forum: Programming
- Topic: Multiple-select listbox option for @uidialog
- Replies: 1
- Views: 2785
Multiple-select listbox option for @uidialog
How can we display a multiple-select listbox (@uimlist) within @uidialog? I was expecting a control type for this newest addition. Something like "mlist", maybe?
- Fri May 27, 2016 7:11 am
- Forum: Estimation
- Topic: Stochastic volatility with MA(1) errors in sspace
- Replies: 2
- Views: 4541
Re: Stochastic volatility with MA(1) errors in sspace
1) Yes, your specification is correct. Yes, how do you justify the MA behavior in such a heavily transformed dependent variable from a theoretical/practical standpoint? Have you tried using simpler models to find any evidence in favor? 2) Yes, c(4) should equal to 1 in this case. However, you cannot...
- Fri May 27, 2016 6:31 am
- Forum: Add-in Support
- Topic: OGARCH
- Replies: 2
- Views: 9384
Re: OGARCH
You can send me a private message explaining the reason of your interest in detail along with your e-mail address.
- Fri May 27, 2016 6:30 am
- Forum: Add-in Support
- Topic: HDecomp (historical decomposition)
- Replies: 32
- Views: 83199
Re: HDecomp (historical decomposition)
What do you think historical decomposition does? Yes, it is possible and would make perfect sense.
- Fri May 27, 2016 6:25 am
- Forum: Add-in Support
- Topic: DCCGARCH11
- Replies: 121
- Views: 438044
Re: DCCGARCH11
Since the univariate GARCH model should be applied on the residuals of these two series, I am wondering if I have to put the variable "stock returns" and "bond returns" in the first box or their residuals ? (so "residuals stock returns" and "residuals bond returns...
- Tue May 03, 2016 12:02 am
- Forum: Econometric Discussions
- Topic: Structural VAR
- Replies: 2
- Views: 4062
Re: Structural VAR
You can either define 4 domestic factors as endogenous variables and treat the other two as exogenous variables as Dakila suggests (along with the constant), or make a 6-variable VAR and then orthogonalize the error terms (with structural factorization or a simple Cholesky decomposition) to make sur...
- Mon May 02, 2016 11:48 pm
- Forum: Programming
- Topic: check code
- Replies: 5
- Views: 5766
Re: check code
Open a program window (File->New->Program), copy-and-paste the script and then hit Run. All the information produced will be stored in the workfile.
- Fri Apr 29, 2016 3:26 am
- Forum: Programming
- Topic: check code
- Replies: 5
- Views: 5766
Re: check code
If you are not familiar with EViews, I suggest you to learn the basics before doing such complex analyses. Other than that, use the modified code below instead: wfcreate u 500 'create an undated workfile with 500 observations. !reps = 10000 'number of simulations matrix(!reps,2) resultados 'create a...