Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | SR Millis <aa3379@wayne.edu> |
To | statalist@hsphsun2.harvard.edu |
Subject | RE: st: collin |
Date | Sat, 12 Mar 2011 06:39:27 -0800 (PST) |
I would suggest that your examine the condition indexes: see if that are any that exceed 20-30. For those that do, examine their associated variance decomposition proportions: see if any exceed .50. For those that do, identify their associated variables---and you will find the sources of high collinearity. SR Millis --- On Sat, 3/12/11, DE SOUZA Eric <eric.de_souza@coleurope.eu> wrote: > From: DE SOUZA Eric <eric.de_souza@coleurope.eu> > Subject: RE: st: collin > To: "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu> > Date: Saturday, March 12, 2011, 6:16 AM > I haven't been following this thread > till now. > Jeffrey Wooldridge in his introductory textbook (page 99, > international edition) does not encourage use of the VIF . > The variance of a coefficient depends on three factors: the > standard error of the regression, the total sample variation > in the variable attached to the coefficient and the partial > R2 . Concentrating on the partial R2 has no justification, > even less so the rule of 10. > > However, in this case, the referee will probably have to be > satisfied in some way or the other. > > Aggie, when you say that the dummies were dropped on > account of collinearity, what exactly do you mean? > > Eric > > > Eric de Souza > College of Europe > Brugge (Bruges), Belgium > http://www.coleurope.eu > > > -----Original Message----- > From: owner-statalist@hsphsun2.harvard.edu > [mailto:owner-statalist@hsphsun2.harvard.edu] > On Behalf Of Syed Basher > Sent: 12 March 2011 11:57 > To: statalist@hsphsun2.harvard.edu > Subject: Re: st: collin > > Dear Aggie, > > I recently used VIF in one of my papers. You can find the > discussion here: > http://ideas.repec.org/p/pra/mprapa/27348.html > -- See p. 14 (footnote 23) and p. 22 > > A general rule of thumb in economics is a VIF>10 > indicates harmful collinearity. > Hope you find this useful. > > Syed Basher > Doha, Qatar. > > > > > ----- Original Message ---- > From: Aggie Chidlow <mojamalarybka@googlemail.com> > To: statalist@hsphsun2.harvard.edu > Sent: Sat, March 12, 2011 1:36:26 AM > Subject: Re: st: collin > > Dear Charls and Syed, > Thank you very much for your comments and suggestions. > > I would be thankful very much for your help Syed regarding > how to interpret VIF professionaly. Any advice/references > would be very much appreciated. > > Many thanks,Aggie > > On Thu, Mar 10, 2011 at 3:14 PM, Syed Basher <syed.basher@yahoo.com> > wrote: > > Hi Aggie, > > > > I think diagnostic checking such as VIF comes before > estimation, that > > is we first check the extent of collinearity among > variables using VIF > > then decide which variables to include in the > estimation. After > > running VIF, you can do > two > > sets of estimation: one with all dummies (what the > reviewer asked for) > > and another with least collinear dummies (as you > already did), this > > way the difference between two results will show up. > As Charles > > mentioned, it is > better > > to follow what the reviewer has asked for. If you > wanted to know how > > to interpret VIF results professionally, let me know. > > > > Syed Basher > > Doha, Qatar > > > > > > > > ----- Original Message ---- > > From: Aggie Chidlow <mojamalarybka@googlemail.com> > > To: statalist@hsphsun2.harvard.edu > > Sent: Thu, March 10, 2011 4:30:51 PM > > Subject: st: collin > > > > Dear Stata users, > > > > I was appreciate some help regarding "collin" > > > > I just got a paper back from a reviewer and he/she > wants me to include > > all my year dummies (i.e. y98 y99 y00 y01 y02 y03) in > the following > > model: probit y x1 x2 x3 lnx4 x5 y98 y99 > y00 y01 y02 > > > > Previusly in the model I only included two year > dummies (i.e y99 and > > y01) as the others we omitted automatically due to > collinearity. > > I mentioned that in the paper, however, he/she says it > is > > unsatisfactory and I should include them all and than > comment on VIF. > > > > Please, can somebody tell me how I can go about this? > > Any advise and/or references will be more than > appreciated. > > > > Many thanks in advance. > > Aggie > > * > > * For searches and help try: > > * http://www.stata.com/help.cgi?search > > * http://www.stata.com/support/statalist/faq > > * http://www.ats.ucla.edu/stat/stata/ > > > > > > > > > > * > > * For searches and help try: > > * http://www.stata.com/help.cgi?search > > * http://www.stata.com/support/statalist/faq > > * http://www.ats.ucla.edu/stat/stata/ > > > > * > * For searches and help try: > * http://www.stata.com/help.cgi?search > * http://www.stata.com/support/statalist/faq > * http://www.ats.ucla.edu/stat/stata/ > > > > > * > * For searches and help try: > * http://www.stata.com/help.cgi?search > * http://www.stata.com/support/statalist/faq > * http://www.ats.ucla.edu/stat/stata/ > > * > * For searches and help try: > * http://www.stata.com/help.cgi?search > * http://www.stata.com/support/statalist/faq > * http://www.ats.ucla.edu/stat/stata/ > * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/