Search found 3775 matches

by startz
Sun Jan 22, 2023 12:26 pm
Forum: Estimation
Topic: Different R squared value
Replies: 11
Views: 6169

Re: Different R squared value

The Cochrane-Orcutt package is returning the R-squared on the quasi-differenced model. This is a bug. EViews has it right.

(Orcutt would not have been pleased.)
by startz
Sun Jan 22, 2023 8:33 am
Forum: Estimation
Topic: Different R squared value
Replies: 11
Views: 6169

Re: Different R squared value

What command did you use in R? I don't think

Code: Select all

lm()
does Cochrane-Orcutt, does it?

(By the way, I'd be willing to wager that the R-squared shown in the R output is from the quasi-differenced variables.)
by startz
Fri Jan 13, 2023 7:09 am
Forum: Programming
Topic: Loop function for AR(1) series
Replies: 1
Views: 998

Re: Loop function for AR(1) series

Code: Select all

smpl 2000m01 2020m12
series y = 0
smpl 2000m02 2020m12
y = 3*y(-1) + 24/5
smpl 2000m01 2020m12
by startz
Sat Dec 17, 2022 7:55 am
Forum: Programming
Topic: create object that activates a command when being opened/clicked on
Replies: 19
Views: 5559

Re: create object that activates a command when being opened/clicked on

[quote="EViews Gareth"]I just knocked one up that lets me open up the latest cricket scores from an object in an EViews workfile (why haven't we added this as a built in feature?!)

Of what possible use it it to explain crickets to Americans?
by startz
Sat Nov 12, 2022 7:32 am
Forum: Econometric Discussions
Topic: What's the best estimation option?
Replies: 2
Views: 3055

Re: What's the best estimation option?

The best option is an ordered logit or probit. Just be sure not to include a constant so as to avoid perfect multicollinearity.
by startz
Wed Oct 26, 2022 12:29 pm
Forum: Econometric Discussions
Topic: Is multicollinearty not a big issue in panel data?
Replies: 4
Views: 5721

Re: Is multicollinearty not a big issue in panel data?

True. But multicollinearity is already accounted for in the standard errors that EViews produces.
by startz
Tue Oct 25, 2022 3:55 pm
Forum: Econometric Discussions
Topic: Is multicollinearty not a big issue in panel data?
Replies: 4
Views: 5721

Re: Is multicollinearty not a big issue in panel data?

What do you think the problem is with multicollinearity when it's not panel data?
by startz
Mon Oct 24, 2022 2:22 pm
Forum: Suggestions and Requests
Topic: Smarter clipping at graph limits
Replies: 0
Views: 7375

Smarter clipping at graph limits

Here's a scatter of 0/1 data using the default settings. It would be nice if the upper limit of the Y-axis didn't go to 2. More importantly, it would be nice if the default lower limit didn't lead to the default symbols being clipped. All this can be fixed by fiddling with the axis limits, but a nic...
by startz
Mon Oct 03, 2022 10:53 am
Forum: General Information and Tips and Tricks
Topic: evsettings file
Replies: 1
Views: 3639

evsettings file

Mostly out of idle curiosity, what's the evsettings file and does it matter if we delete it?
by startz
Mon Sep 26, 2022 7:45 am
Forum: Estimation
Topic: getting out of an overflow
Replies: 4
Views: 2848

Re: getting out of an overflow

yes... indeed! the starting values are those appearing in the vector c? should I go to the vector c and change one by one the values? It's very hard to know which starting value is causing the problem. You might want to set them all at values you think are reasonable. If that doesn't work then, yes...
by startz
Mon Sep 26, 2022 6:06 am
Forum: Estimation
Topic: getting out of an overflow
Replies: 4
Views: 2848

Re: getting out of an overflow

You probably want to change the starting values (in the C vector).
by startz
Sun Sep 11, 2022 7:16 am
Forum: Bug Reports
Topic: TAB key is not working
Replies: 2
Views: 1626

Re: TAB key is not working

I can confirm the bug (latest patch).
by startz
Wed Aug 24, 2022 12:20 pm
Forum: Bug Reports
Topic: blewey
Replies: 1
Views: 1462

blewey

Just killed 13 (did it twice to be sure to be sure)
Drop and drag attached file onto EViews. In the dialog that shows (which I suspect is the wrong dialog) hit All.

Blewey!

ETA: Loading the file through File/Open also blows-up EViews. (File was saved in most recent version of R.)
by startz
Sun Aug 14, 2022 10:14 am
Forum: Programming
Topic: Generate a series based on 3 conditions
Replies: 3
Views: 2249

Re: Generate a series based on 3 conditions

Hi everyone, I want to generate series w(t) with the following conditions: w(t)=0 if a(t)<0 w(t)=a(t) if 0=<a(t)<=1 w(t)=1 if a(t)>1 Could anyone please help me on this command? Normally with 2 conditions , I use @recode, but I don't know for 3 conditions. wt = @recode(a<0,0,a) wt = @recode(a>1,1,w...
by startz
Sat Jul 09, 2022 6:43 am
Forum: Estimation
Topic: Marginal effect plot
Replies: 3
Views: 2561

Re: Marginal effect plot

You'll need to retrieve the variance-covariance matrix of the coefficients from the regression. Then get the variance of the point estimate using the standard formula for linear combinations of random variables. Take the square root, and then take the point estimates plus and minus twice that square...

Go to advanced search