EViews.com

Hello, When using "xget" to retrieve data from an external application into an EViews object, the "type=" option does not include graphical objects. I realise that the graphical formats are very different, but was wondering whether via your usual magic you had nevertheless found ...

FYI, RATS can estimate an SVAR with both SR and LR restrictions
Regards
Donihue

Hello Gareth,

Thanks for your reply. I think you have solved my problem with your query about databases: I was trying to store to a GiveWin database, not an EViews database. It works perffectly when using a native EViews database.

Regards
Donihue

According to the online help files for EViews 7.2, As with other objects, equations may be stored to disk in data bank or database files. You can also fetch equations from these files. Equations may also be copied-and-pasted to, or from, workfiles or databases. EViews even allows you to access equat...

Unfortunate - it would make the use of (non-Johansen-based) error-correction models much easier!

Regards
Donihue

In the context of a multi-equation model, I would like to be able to write an equation specification which uses equation residuals dynamically - i.e., looks something like "equation eq2.ls dlog(y) dlog(x) eq1.resid(-1)" so that if the specification of eq1 changes, the residual used in eq2 ...

Your model is neither VEC nor VAR and you have no equation for "scnq". You should simply set up a system with the equations you have specified (Object==> New object==> System; then in the system object Proc==>Define System)

Regards
Donihue

Re your query on my point 2, it is in line with tcfoon's point 1 (GROWTH is very unlikely to be I(1)). If you want to estimate a VAR, use I(0) variables; if you want to estimate cointegrating relationships, you need all variables to be of the same degree of integration (typically I(1)), Regards Doni...

Some suggestions: 1. HUMAN CAPITAL and GOVERNMENT SPENDING are naturally exogenous in this model. If TRADE OPENNESS is measured as the share of X+M in GDP, then you have an endogeneity issue 2. Most economists consider that variables in a VAR should be I(0), NOT I(1). Typically, this is achieved by ...

If you draw the starting values from a Uniform(0,1) distribution, your SVAR converges; however, the LR test indicates that the (over-)identification restrictions are strongly rejected, thus indicating that the proposed SVAR is rejected by the data, implying the need to change the underlying restrict...

Hello Esther, I doubt that you any longer take an interest in the old MSBVAR version of your excellent add-in, but as I wanted to be able to use exogenous variables with it, I re-wrote it to enable that. I attach the revised version in case it may be of interest. I have tested it against both the cu...

Hello Gareth, I asked Scilab if they had COM support, and below is the answer I received from Allan Cornet, the "guru" of Scilab: Hi, There are many ways to interact with Scilab You can call Scilab engine from C/C++, java, C# See http://help.scilab.org/docs/5.3.2/en_US/section_0b209c9ffb9f...

"Help" indicates that EViews offers COM Automation client support for select external application servers. Support is currently provided for two applications: MATLAB and R. . Would it be possible to add Scilab ( http://www.scilab.org ) - which is a (free) alternative to Matlab - to that li...

Thank you very much indeed, Steve. That worked a treat!
Regards
Donihue

Many thanks for your time, Steve. The class of M_.params is the same as that of, say, the scalar sigas referenced in my output (namely, "double"), but the command "cell2mat(M_.params)" in Matlab just returns an error: ??? Cell contents reference from a non-cell array object. Erro...