Search found 2549 matches

by EViews Glenn
Fri Nov 17, 2017 11:34 am
Forum: Econometric Discussions
Topic: overlapping graphs
Replies: 1
Views: 54

Re: overlapping graphs

Which Markov switching graph?
by EViews Glenn
Fri Nov 17, 2017 11:32 am
Forum: Estimation
Topic: Cochrane Orcutt
Replies: 9
Views: 139

Re: Cochrane Orcutt

It's actually not iterated Corchrane-Orcutt. It's straight non-linear least squares. In general, this doesn't matter, but sometimes does for instrumental variables. I believe we have a discussion of this in the manual.
by EViews Glenn
Mon Nov 13, 2017 11:15 pm
Forum: Estimation
Topic: Eviews 9 clustered standard errors
Replies: 2
Views: 111

Re: Eviews 9 clustered standard errors

You want White period as this allows for within cross section between period correlation.

Yes. http://www.eviews.com/EViews10/ev10ecest_n.html#cluster
by EViews Glenn
Mon Nov 13, 2017 6:59 pm
Forum: Estimation
Topic: one-way unbalanced random effect model (Swamy/Arora)
Replies: 8
Views: 332

Re: one-way unbalanced random effect model (Swamy/Arora)

( My apologies. I am often too busy to get back here very often and missed your followup posting. I had thought that I had answered the question and I just saw the updated thread today. Please feel free to followup on the discussion with the wider audience at cross validated. ) ------- That said, I ...
by EViews Glenn
Thu Nov 09, 2017 10:44 am
Forum: Bug Reports
Topic: Seasonal autoregression typo
Replies: 1
Views: 65

Re: Seasonal autoregression typo

Yes. We'll get it fixed. Thank you.
by EViews Glenn
Mon Oct 30, 2017 10:33 am
Forum: Bug Reports
Topic: Unit Root test with structural break
Replies: 1
Views: 142

Re: Unit Root test with structural break

There appears to be a bug in the parsing engine. We have code which carefully makes certain to consider only relevant breakpoint selection so that we don't parse options for invalid methods. Unfortunately, the code is currently also ignoring one or two valid methods in your case. For the moment, you...
by EViews Glenn
Mon Oct 30, 2017 10:28 am
Forum: Programming
Topic: Overflow when making residuals series
Replies: 4
Views: 193

Re: Overflow when making residuals series

We're going to have to see the workfile with the estimated system object.
by EViews Glenn
Wed Oct 25, 2017 12:20 pm
Forum: Programming
Topic: Overflow when making residuals series
Replies: 4
Views: 193

Re: Overflow when making residuals series

Are these residuals post-estimation or during estimation?
by EViews Glenn
Mon Oct 23, 2017 10:02 pm
Forum: Estimation
Topic: one-way unbalanced random effect model (Swamy/Arora)
Replies: 8
Views: 332

Re: one-way unbalanced random effect model (Swamy/Arora)

The overall scaling is built into our GLS transform. I don't have my books handy, but it strikes me that one reason for GLS coefficient covariance differences arises because there are multiple consistent estimators. One approach uses the (X' Omega^-1 X)^-1. This is a consistent estimator and probabl...
by EViews Glenn
Mon Oct 23, 2017 10:58 am
Forum: Data Manipulation
Topic: two way panel
Replies: 9
Views: 350

Re: two way panel

True. I forget that you are unbalanced.
by EViews Glenn
Mon Oct 23, 2017 10:57 am
Forum: Estimation
Topic: one-way unbalanced random effect model (Swamy/Arora)
Replies: 8
Views: 332

Re: one-way unbalanced random effect model (Swamy/Arora)

Not the correct estimator. The standard GLS estimator is
var(b) = (X' Omega^-1 X)^-1

So for the quasi-demeaned data, you'll have
var(b) = (Z'Z)^-1
by EViews Glenn
Mon Oct 23, 2017 10:56 am
Forum: Programming
Topic: DOLS - estimated equation. Corresponding OLS
Replies: 3
Views: 156

Re: DOLS - estimated equation. Corresponding OLS

Are you using the default DOLS coefficient variance estimator? If so, the options may be the same, but it is computing a different estimator of the coefficient variance.
by EViews Glenn
Fri Oct 20, 2017 3:37 pm
Forum: Data Manipulation
Topic: two way panel
Replies: 9
Views: 350

Re: two way panel

The @expand should work for the remaining dimension, no?
by EViews Glenn
Fri Oct 20, 2017 1:28 pm
Forum: Data Manipulation
Topic: two way panel
Replies: 9
Views: 350

Re: two way panel

If you have three variables, say Y, X1, and X2, you can easily demean using frml ydm = y - @meansby(y, id) frml x1dm = x - @meansby(x1, id) frml x2dm = x - @meansby(x2, id) where ID is the categorization variable corresponding to the 10,000 dummies. The result will be the series with means-by-catego...
by EViews Glenn
Fri Oct 20, 2017 1:25 pm
Forum: Programming
Topic: DOLS- fitted values
Replies: 3
Views: 183

Re: DOLS- fitted values

If you want truly want the fitteds, use the actual minus the residuals. Those will include the short-run dynamics which are relevant for analyzing the fit.

For out-of-sample forecasting, people are generally only concerned with the long-run forecasts from the cointegrating relationship.

Go to advanced search