Search found 3172 matches

by startz
Fri Nov 17, 2017 6:14 pm
Forum: Estimation
Topic: Cochrane Orcutt
Replies: 9
Views: 138

Re: Cochrane Orcutt

Unfortunately, having an AR(1) coefficient above 1 means that many things in the regression don't work as it implies the errors do not have a finite variance. Adding an AR(2) is the right thing to do. The fact that the results aren't as expected doesn't make it wrong. My guess is that your dependent...
by startz
Fri Nov 17, 2017 7:51 am
Forum: Estimation
Topic: Cochrane Orcutt
Replies: 9
Views: 138

Re: Cochrane Orcutt

By Iterated CO, you mean the part where it says Convergence achieved after XX iterations, right? right I've changed my estimation method to CLS. One thing worries me. My R squared is extremely high (0.997). Is that normal? Also, seeing as to how I've already corrected for the AR(1) via CO and Feasi...
by startz
Fri Nov 17, 2017 6:56 am
Forum: Estimation
Topic: Cochrane Orcutt
Replies: 9
Views: 138

Re: Cochrane Orcutt

Yes, although EViews does iterated Cochrane-Orcutt.
by startz
Thu Nov 16, 2017 11:50 am
Forum: Bug Reports
Topic: ugly
Replies: 0
Views: 36

ugly

Dialogs need to be better at dealing with different screen settings.
Capture.PNG
Capture.PNG (6.87 KiB) Viewed 21 times
by startz
Thu Nov 16, 2017 10:23 am
Forum: Suggestions and Requests
Topic: key for command window
Replies: 0
Views: 32

key for command window

Would be nice if there were a shortcut key to open up the command window and shift focus to it. (Also, keyboard shortcuts and function keys don't seem to show up in the index of the help system.)
by startz
Wed Nov 15, 2017 4:15 pm
Forum: Bug Reports
Topic: bottom scale not adjusting
Replies: 2
Views: 64

Re: bottom scale not adjusting

Yes it is a date axis.

In this case, I'm not so sure that "correctly" and "as designed" mean the same thing.
by startz
Wed Nov 15, 2017 10:51 am
Forum: Bug Reports
Topic: bottom scale not adjusting
Replies: 2
Views: 64

bottom scale not adjusting

Telling the bottom scale to adjust doesn't seem to be working, unless I misunderstand something. See the picture.
Capture.PNG
Capture.PNG (46.45 KiB) Viewed 45 times
by startz
Tue Nov 14, 2017 11:54 am
Forum: Suggestions and Requests
Topic: copy colors in graphs
Replies: 0
Views: 41

copy colors in graphs

It would be really, really nice if there were an easy way to copy the colors in a graph. For example, to make two lines have the same color. Or even to copy the color from one graph to another.
by startz
Mon Nov 13, 2017 3:21 pm
Forum: Suggestions and Requests
Topic: Fiscal/Academic year labeling
Replies: 0
Views: 38

Fiscal/Academic year labeling

It would be nice if EViews could accommodate annual data of the sort, 2016-17, 2017-18, etc. Even if it's only for labeling graphs and the like.
by startz
Thu Nov 09, 2017 3:08 pm
Forum: Suggestions and Requests
Topic: Title for ARMA structure graphs
Replies: 2
Views: 74

Re: Title for ARMA structure graphs

I do.
by startz
Thu Nov 09, 2017 2:38 pm
Forum: Suggestions and Requests
Topic: Title for ARMA structure graphs
Replies: 2
Views: 74

Title for ARMA structure graphs

It would be nice if...
the default titles in graphs produced under ARMA structure included the variable name being graphed.
by startz
Wed Nov 08, 2017 6:21 pm
Forum: Bug Reports
Topic: blewey yet again
Replies: 1
Views: 82

blewey yet again

Froze a graph (If relevant, a graph of the frequency spectrum from an AR model).
Under Axes & scaling Obs/Daya axis changed Observations to label Steps to .1.

Blewey!

(Did it twice.)
by startz
Mon Nov 06, 2017 3:32 pm
Forum: Estimation
Topic: Dummy Variables
Replies: 133
Views: 103404

Re: Dummy Variables

How many dummies would you guess you can run through @expand before either the numerics break or the regression takes forever?
by startz
Mon Nov 06, 2017 12:22 pm
Forum: Estimation
Topic: Dummy Variables
Replies: 133
Views: 103404

Re: Dummy Variables

@expand(industry)
by startz
Mon Nov 06, 2017 6:47 am
Forum: Data Manipulation
Topic: Selecting observation in particular quarter
Replies: 3
Views: 146

Re: Selecting observation in particular quarter

Something like
smpl if @quarter=1

Go to advanced search