[Gretl-devel] cnumber / multicollinearity (Lee?) (Re: Proposal for function package cleanup)

Lee Adkins lee.adkins at okstate.edu
Mon Jul 13 10:58:00 EDT 2015


OK.  I've looked at cnumber and though correctly executed, it is too
limited in my opinion.  It only produces the single largest condition
number (no variance decomposition) for a linear model.  Proper diagnostics
for collinearity may involve the others as well.

My other complaint is trivial: the included example excludes the intercept
as a regressor.  As BKW argue, and Hill and Adkins (2001) agree (shameless
plug), the intercept should ordinarily be included if the model is
estimated with one .  When the intercept is included in cnumber the
computations are correct.  So the function is doing what it is supposed to
do,

The proposed bkw.gfn function produces the whole set of condition numbers
and the BKW variance decompositions --without centering-- for any estimated
model (linear or nonlinear) for which gretl returns a variance covariance.



On Sun, Jul 12, 2015 at 9:11 PM, Lee Adkins <lee.adkins at okstate.edu> wrote:

> I've got mine packaged, but haven't looked at cnumber yet and was
> reluctant to submit mine until I did.  Will do so tomorrow.... Thanks,
> Sven.....
>
> Lee
>
> On Sun, Jul 12, 2015 at 3:35 PM, Sven Schreiber <svetosch at gmx.net> wrote:
>
>> Am 16.06.2015 um 18:49 schrieb Sven Schreiber:
>>
>> >
>> > 2) cnumber (Monsueto) -- maybe I'm confusing things, but could this be
>> > redundant when the stuff that Lee just presented at the conference is
>> > packaged? (I guess it could stay until then.)
>>
>> Please give some feedback on whether this hunch of mine is correct. Lee,
>> are you planning to package your stuff and would it be a substitute
>> (superset in some sense) of this functionality?
>>
>> Thanks,
>> sven
>>
>>
>>
>> _______________________________________________
>> Gretl-devel mailing list
>> Gretl-devel at lists.wfu.edu
>> http://lists.wfu.edu/mailman/listinfo/gretl-devel
>>
>
>
>
> --
> Lee Adkins
> Professor of Economics and Department Head
> Economics and Legal Studies in Business
> Oklahoma State University
>
> Email:  lee.adkins at okstate.edu
> Fax: 405-744-5180
> Phone: 405-744-5196
> URL:  www.learneconometrics.com
>
>


-- 
Lee Adkins
Professor of Economics and Department Head
Economics and Legal Studies in Business
Oklahoma State University

Email:  lee.adkins at okstate.edu
Fax: 405-744-5180
Phone: 405-744-5196
URL:  www.learneconometrics.com
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.wfu.edu/pipermail/gretl-devel/attachments/20150713/971fdcd3/attachment.html>


More information about the Gretl-devel mailing list