Search found 524 matches

by EViews Matt
Wed May 18, 2022 8:12 pm
Forum: Models
Topic: Adding @stochastic to a model text file
Replies: 4
Views: 130

Re: Adding @stochastic to a model text file

Hello,

Perhaps what you're looking for is the Model::innov procedure.
by EViews Matt
Thu May 12, 2022 11:24 am
Forum: General Information and Tips and Tricks
Topic: Dependency Graph Export
Replies: 2
Views: 430

Re: Dependency Graph Export

Hello, Which software are you using to import the GraphML file generated by EViews? Unfortunately, as with many data formats in the XML family, GraphML is more a syntactic specification than a semantic specification. By this I mean that while a GraphML file can store many types of information about ...
by EViews Matt
Mon May 02, 2022 10:20 am
Forum: Estimation
Topic: Impulse Response Function
Replies: 2
Views: 238

Re: Impulse Response Function

Hello,

Since you've using an SVAR factorization, the impulse responses are in term of innovations to the structural variables, not the original variables, e.g. government expenditure or GDP. By construction, the one S.D. structural innovations and the one unit structural innovations are identical.
by EViews Matt
Tue Apr 05, 2022 4:32 pm
Forum: Estimation
Topic: BFGS stopping criterion and numerical difference tuning
Replies: 3
Views: 551

Re: BFGS stopping criterion and numerical difference tuning

Hello, For this scenario, the documentation of the 'c' parameter is a bit misleading. Elaborating on my answer (3) above, the termination criterion actually examines the trust region size associated with each quasi-Newton step, ending the algorithm when the trust region shrinks below the value of th...
by EViews Matt
Thu Mar 24, 2022 11:30 am
Forum: Estimation
Topic: BFGS stopping criterion and numerical difference tuning
Replies: 3
Views: 551

Re: BFGS stopping criterion and numerical difference tuning

Hello, Let me try to address your three main points... (1) As of EViews 10, the speed vs. accuracy general option no longer applies to state-space estimation via FIML w/ BFGS. Formerly, that option did select between Taylor series order, basically either 2-point or 4-point numeric derivatives (with ...
by EViews Matt
Mon Mar 07, 2022 11:29 am
Forum: Estimation
Topic: VAR estimation questions: estimation method and serial correlation
Replies: 2
Views: 436

Re: VAR estimation questions: estimation method and serial correlation

Hello, More in-depth answers to all of your questions can be found in the EViews documentation for VARs, but to summarize, (1) unrestricted reduced-form VARs are estimated by OLS, (2) the LRE statistic is the Edgeworth expansion correction form of the LM test, and (3) the LM test is the Breusch-Godf...
by EViews Matt
Wed Jan 19, 2022 3:14 pm
Forum: Programming
Topic: Using Git when programming add-in
Replies: 5
Views: 17263

Re: Using Git when programming add-in

This all depends greatly on your workflow and Git setup, but for this example suppose we have a local Git repository with the "master"/"main" branch and a "dev" branch. We want different versions of an addin registered in EViews depending on which branch is currently ac...
by EViews Matt
Tue Jan 11, 2022 6:19 pm
Forum: Models
Topic: Simulations: Add-factor interaction with ARMA errors
Replies: 6
Views: 23562

Re: Simulations: Add-factor interaction with ARMA errors

Hello, Addressing your last point first, stochastic innovations do interact with ARMA errors as you'd expect. Add factors are the oddity. In effect, residuals/innovations are determined before add factors are applied, so add factors don't propagate through ARMA terms. Your approach for implementing ...
by EViews Matt
Tue Jan 11, 2022 3:49 pm
Forum: Programming
Topic: Code to determine date of first Friday of the year
Replies: 5
Views: 7673

Re: Code to determine date of first Friday of the year

My apologies, I pasted a genr expression for the calculation instead of a scalar context expression. Just replace to two @date references with @now... %mydate = @datestr(@datefloor(@now, "y") + 6 - @mod(@datepart(@datefloor(@now, "y"), "w") + 1, 7), "mm/dd/yyyy&quo...
by EViews Matt
Tue Jan 11, 2022 11:39 am
Forum: Programming
Topic: Code to determine date of first Friday of the year
Replies: 5
Views: 7673

Re: Code to determine date of first Friday of the year

Hello,

I believe this will work:

Code: Select all

%mydate = @datestr(@datefloor(@date, "y") + 6 - @mod(@datepart(@datefloor(@date, "y"), "w") + 1, 7), "mm/dd/yyyy")
by EViews Matt
Thu Jan 06, 2022 5:59 pm
Forum: Programming
Topic: Using Git when programming add-in
Replies: 5
Views: 17263

Re: Using Git when programming add-in

A quick note, addin registration is available programmatically. You could for example, write your own addin that switched the registration of other addins between their official and development versions, or even use a git hook to trigger the switch.
by EViews Matt
Thu Jan 06, 2022 5:27 pm
Forum: Models
Topic: Simulations: Add-factor interaction with ARMA errors
Replies: 6
Views: 23562

Re: Simulations: Add-factor interaction with ARMA errors

Hello,

Sorry your post escaped my notice earlier. Unfortunately, add factors are not treated as innovation shocks even in stochastic solves and there are no options for altering this behavior.
by EViews Matt
Thu Jan 06, 2022 8:45 am
Forum: Models
Topic: FLIPTYPE
Replies: 8
Views: 16124

Re: FLIPTYPE

Hello,

Using the message window, the parsing loop of two posts back could be modified to look for the individual "Dropped add factor series " lines and extract them all that way.
by EViews Matt
Wed Jan 05, 2022 10:37 am
Forum: Models
Topic: FLIPTYPE
Replies: 8
Views: 16124

Re: FLIPTYPE

I knew you'd ask that. :lol: In which case, to avoid parsing each specification for the first variable name perhaps it's best to include an add factor on all equations, thus the set of dropped add factors will match the set of modified equations.
by EViews Matt
Tue Jan 04, 2022 3:12 pm
Forum: Models
Topic: FLIPTYPE
Replies: 8
Views: 16124

Re: FLIPTYPE

Another good candidate for a new data member. Otherwise, a brief loop can extract the information... logmode l create u 1 ' Create a trivial model with 50 equations. model m for !i = 1 to 50 m.append x!i = y!i next m.addassign @all ' We're going to flip the first 25 equations. for !i = 1 to 25 %tmp ...

Go to advanced search