Search found 2598 matches

by EViews Glenn
Thu Feb 19, 2009 11:19 am
Forum: Estimation
Topic: ML - Intial Parameters
Replies: 1
Views: 1272

Re: ML - Intial Parameters

The default is whatever is in the corresponding coefficient vector when you begin the estimation procedure.
by EViews Glenn
Tue Feb 17, 2009 12:17 pm
Forum: Programming
Topic: a program to calculate predictive probabilities
Replies: 1
Views: 1228

Re: a program to calculate predictive probabilities

Make a model object from your estimated equation using Proc/Make Model (or the command equivalent). This will give you a set of equations each of which corresponds to the category probabilities. Simply solve the model to evaluate at the observed data for a given sample, or use the tools in the model...
by EViews Glenn
Mon Feb 16, 2009 10:51 am
Forum: EViews 5 and Earlier
Topic: Different results with EViews5 and STATA
Replies: 11
Views: 15924

Re: Different results with EViews5 and STATA

While your point about there being perhaps unsurprising differences in implementation is certainly true, I do want to note that In the program Stata Levin-Lin program in question is not an official Stata routine with all of the vetting that that entails, but rather one written by users for their par...
by EViews Glenn
Fri Feb 13, 2009 2:17 pm
Forum: Estimation
Topic: predetermined intercept/coefficients?
Replies: 2
Views: 1564

Re: predetermined intercept/coefficients?

Or put the left-hand-side variable expression in parentheses:

ls (y - x1) c x2
by EViews Glenn
Wed Feb 11, 2009 7:44 am
Forum: Programming
Topic: Principal Components Analysis
Replies: 26
Views: 15211

Re: Principal Components Analysis

Possibly the best way for you is to, instead of storing everything onto disk in your loop, put your results in a spool object. Then you can look at individual results in EViews. You'll have to look at the docs for a discussion of how to do this...
by EViews Glenn
Tue Feb 10, 2009 5:17 pm
Forum: EViews 5 and Earlier
Topic: Different results with EViews5 and STATA
Replies: 11
Views: 15924

Re: Different results with EViews5 and STATA

I've spent a bit of time looking into the differences between the Stata/ levinlin and EViews results and have some answers. The following discussion refers to both EViews 5.1 and EViews 6, in comparison with the 1.1.5 version of the levinlin ado. There are four reasons for differences between the le...
by EViews Glenn
Fri Feb 06, 2009 2:24 pm
Forum: Programming
Topic: Principal Components Analysis
Replies: 26
Views: 15211

Re: Principal Components Analysis

I'm afraid that I don't quite understand what it is you are trying to do. What exactly do you mean by displaying the results one by one?
by EViews Glenn
Fri Feb 06, 2009 2:21 pm
Forum: EViews 5 and Earlier
Topic: Different results with EViews5 and STATA
Replies: 11
Views: 15924

Re: Different results with EViews5 and STATA

Most probably a d.f. correction issue. Can you send your workfile to support@eviews.com.

We might not get a chance to look at it until next week as there are quite a few things going on right now, but we'll see if we can take a look.
by EViews Glenn
Thu Feb 05, 2009 10:23 am
Forum: EViews 5 and Earlier
Topic: Extreme Value Theory
Replies: 2
Views: 3143

Re: Extreme Value Theory

The first part of this request is somewhat broad and difficult to answer. EViews does not have tools designed specifically for perform extreme value theory analysis, but does have tools that are relevant. Extreme value theory is not something I've had a lot of experience with, but my brief look at a...
by EViews Glenn
Thu Feb 05, 2009 9:46 am
Forum: EViews 5 and Earlier
Topic: Different results with EViews5 and STATA
Replies: 11
Views: 15924

Re: Different results with EViews5 and STATA

Not being familiar with the Stata Levinlin package I can't say for certain, but given the relative simplicity of Levin-Lin-Chu, I would guess that it has to do with differences in degree-of-freedom corrections for the variances used in the ADFs. This isn't a theoretical difference, but rather a prac...
by EViews Glenn
Tue Feb 03, 2009 10:18 am
Forum: Estimation
Topic: Ordered probit model
Replies: 16
Views: 18723

Re: Ordered probit model

FIrst off, what version of EViews are you using and what's the build-date (Help/About EViews)? I know that we've made some improvements in the automatic determination of starting values in recent versions of EViews that may help. Apart from that, there is an option in estimation to use the starting ...
by EViews Glenn
Mon Feb 02, 2009 10:24 am
Forum: Data Manipulation
Topic: Create series for multinomial logit
Replies: 2
Views: 2232

Re: Create series for multinomial logit

Another method:

Code: Select all

x.classify(method=limits, rightclosed) 0 2.5 7.5 @ y

The one issue here is that the encoding will start from 1 instead of 0. You can, using the same proc, define value maps for the encoding which will be attached to the resulting series.
by EViews Glenn
Mon Feb 02, 2009 10:17 am
Forum: Installation and Registration
Topic: Where to find Chap 1 sample files
Replies: 2
Views: 4097

Re: Where to find Chap 1 sample files

Just to clarify. The book to which the poster is referring is the "EViews Illustrated" book by Richard Startz, not the EViews 6 manuals themselves. That said, the data should be in the EViews6 installation folder in a folder named "EViews Illustrated Data," if, on installation of...
by EViews Glenn
Fri Jan 30, 2009 3:44 pm
Forum: Programming
Topic: Principal Components Analysis
Replies: 26
Views: 15211

Re: Principal Components Analysis

There's an option when you run programs to continue even if you get errors up to a maximum number...It's set at 1 by default, make it bigger.
by EViews Glenn
Fri Jan 30, 2009 11:41 am
Forum: Programming
Topic: Principal Components Analysis
Replies: 26
Views: 15211

Re: Principal Components Analysis

The post I wrote yesterday does the pcomp for a each firm across all years. As I mentioned then, you are still going to have trouble since for some cross-sections, you have very little data (e.g., firm 1 only had 4 usable observations, with some variables having zero variance to boot). And once agai...

Go to advanced search