Search found 402 matches

by EViews Matt
Fri Jan 17, 2020 10:05 am
Forum: Programming
Topic: compare script version comparison
Replies: 4
Views: 190

Re: compare script version comparison

Hello, I'm afraid EViews does not include that sort of program difference functionality, but there are plenty of third-party utilities specifically designed for that task. WinMerge is one such application that comes to mind, but there are many others. No doubt Google can point you in the right direc...
by EViews Matt
Tue Jan 07, 2020 12:48 pm
Forum: Data Manipulation
Topic: PERCENTILE
Replies: 13
Views: 412

Re: PERCENTILE

After a quick empirical check, it appears that Excel is using the van der Waerden interpolation method. That isn't the default interpolation method for EViews, but it is available, e.g.

Code: Select all

scalar perc_rprice=@quantile(exceldata,0.01,"v")
by EViews Matt
Mon Dec 02, 2019 10:36 am
Forum: Programming
Topic: minimum of constrained nonlinear multivariable function
Replies: 2
Views: 206

Re: minimum of constrained nonlinear multivariable function

Hello,

There is not. Constrained optimization in EViews must be performed by variable transformation.
by EViews Matt
Mon Dec 02, 2019 10:24 am
Forum: Estimation
Topic: How I command Eviews not to estimate coefficient in front of variable X
Replies: 6
Views: 374

Re: How I command Eviews not to estimate coefficient in front of variable X

Hello,

You can also use an explicit equation specification to control which coefficients are estimated, e.g.,

Code: Select all

industry_excess_return = c(1) * (1-betamarketexcess) + c(2) * Betafs + betamarketexcess*MARKET_EXCESS_RETURN + Betafs*fswhole
by EViews Matt
Tue Nov 26, 2019 11:33 am
Forum: Programming
Topic: finding the week containing the first friday of the month
Replies: 2
Views: 208

Re: finding the week containing the first friday of the month

Hello,

I believe the following will accomplish what you requested:

Code: Select all

smpl if @datepart(@date + @mod(12 - @datepart(@date, "W"), 7), "DD") <= 7
by EViews Matt
Thu Nov 21, 2019 10:13 am
Forum: Estimation
Topic: Adding controls to the attached model
Replies: 1
Views: 257

Re: Adding controls to the attached model

Hello,

This may just be a matter of missing line continuation characters (_). I notice two omissions in the code you provided, on the lines "{%sys}.append {%VAR_to_PLOT}{%IDC} =" and "+ C1(28+!J)*shock27_{%IDC}", and your subsequent edits might contain a similar typo.
by EViews Matt
Tue Nov 19, 2019 10:05 am
Forum: Programming
Topic: unrestricted VAR: possible to impose another constant value when forecasting?
Replies: 4
Views: 309

Re: unrestricted VAR: possible to impose another constant value when forecasting?

Unfortunately, there is not. At that point, the model will contain text specifications for each equation, so you'll be forced to parse each equation as a string and replace the constant term. At least the constant term should always be the very last term, which will make the parsing easier.
by EViews Matt
Mon Nov 18, 2019 4:26 pm
Forum: Models
Topic: good way to batch set add factors
Replies: 1
Views: 198

Re: good way to batch set add factors

Hello, 1) Take a look at the model object's addinit procedure. 2) For a single variable, something like the following will work. Introducing a loop will let you handle multiple add factors. !fill_value = GDP_A(@dtoo("2019q3")) smpl 2019q4 @last ' Replace with your forecast sample GDP_A = !...
by EViews Matt
Mon Nov 18, 2019 3:10 pm
Forum: Programming
Topic: unrestricted VAR: possible to impose another constant value when forecasting?
Replies: 4
Views: 309

Re: unrestricted VAR: possible to impose another constant value when forecasting?

Hello, The only way that occurs to me is to 1) create a model object from the estimated VAR, 2) break the link between the model and the VAR, 3) edit the individual equations within the model to replace the constant terms as you see fit, and finally 4) perform the "forecast" as a normal mo...
by EViews Matt
Fri Nov 15, 2019 9:55 am
Forum: Data Manipulation
Topic: Unmerging graphs
Replies: 2
Views: 266

Re: Unmerging graphs

Hello,

I don't know that this can be done programmatically, but via the GUI you can select the central portion of each subgraph, right-click, and choose "Extract selected graph".
by EViews Matt
Wed Nov 13, 2019 5:08 pm
Forum: Programming
Topic: Rename multiple series using string functions
Replies: 4
Views: 387

Re: Rename multiple series using string functions

Hello, You have the right idea, but there's a good deal of unnecessary quotation and substitution in your code. We can simplify the syntax of the body of your for loop as follows: %name = g1.@seriesname(!i) !left = @instr(%name, "AIREMSECT_") + @length("AIREMSECT_") !right = @ins...
by EViews Matt
Tue Nov 12, 2019 10:17 am
Forum: Programming
Topic: Relative Paths
Replies: 12
Views: 2482

Re: Relative Paths

Hello,

There is also the undocumented command @runname that returns the file name of the "top-level" program running (ignoring the effects of include or exec as documented for @runpath).
by EViews Matt
Mon Nov 11, 2019 11:41 am
Forum: Estimation
Topic: Maximum number of iteration exceed error
Replies: 4
Views: 436

Re: Maximum number of iteration exceed error

Hello,

Are you using EViews 10? If so, a different initial value choice seems to work better. Try an initial constant of one (use the "f0=1" option in the svar command).
by EViews Matt
Tue Nov 05, 2019 1:45 pm
Forum: Estimation
Topic: Maximum number of iteration exceed error
Replies: 4
Views: 436

Re: Maximum number of iteration exceed error

Hello,

It's always good to try different types of initial values to see if one more effectively leads to convergence. The default normal distribution appears to work with your data (remove the "F0=U" option from the svar command).
by EViews Matt
Wed Oct 23, 2019 9:03 am
Forum: Programming
Topic: Creating CI in Eviews bug
Replies: 4
Views: 925

Re: Creating CI in Eviews bug

I mean when you create ub_r and lb_r.

Code: Select all

genr ub_r=f1r_impulse+1.134*f1r_impulse_se/@sqrt(6)
genr lb_r=f1r_impulse-1.134*f1r_impulse_se/@sqrt(6)

Go to advanced search