Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | "Santos Silva, J.M.C." <jmcss@essex.ac.uk> |
| To | <statalist@hsphsun2.harvard.edu> |
| Subject | RE: RE: st: Beta values in QREG |
| Date | Mon, 24 Jun 2013 21:50:46 +0100 |
Dear Scott, Indeed it looks like you have a bug in your code that is responsible for the strange results. As for Maarten's argument of "clash of logics", I think I do not agree with it for two reasons. First, you may be interested in estimating quantile regression even if the data have finite second (and higher order) moments; Stata's manual is a somewhat misleading in this respect but quantile regression is much more than just a robust "alternative" to mean regression. Second, even if you are using quantile regression because your y does not have finite second moments, that does not mean that your regressors also do not have second moments; so you may still be able to standardize the Xs even if the y has no moments. Having said that, only you can know whether it makes sense to standardize the particular regressors you have in your model. All the best, Joao > From "Scott Holupka" <scott.holupka@jhu.edu> > To <statalist@hsphsun2.harvard.edu> > Subject RE: st: Beta values in QREG > Date Mon, 24 Jun 2013 09:30:37 -0400 > > No, I'm not getting the same results, which is what I expected, so I wanted > to be sure there wasn't a more fundamental problem I was missing or if I had > just made some mistake in my coding. > > Based on your response, as well as Maarten's, I think my answer is both > that: a) I made some sort of coding mistake that's throwing off the results, > and b) even if I compute it correctly it may not make sense to use because > standardized scores since the reason for using quantile/median regression is > that there is evidence of non-normality, so why adjust by a measure of > central tendency that will be biased. > > Thanks for the advice. > > Scott > > > -----Original Message----- > From: owner-statalist@hsphsun2.harvard.edu > [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Santos Silva, > J.M.C. > Sent: Sunday, June 23, 2013 5:09 AM > To: statalist@hsphsun2.harvard.edu > Subject: RE: st: Beta values in QREG > > Dear Scott, > > What exactly do you mean when you say that running qreg with standardized > variables leads to different results? The results should be exactly the same > (I mean, the R2, objective function, etc), except that the coefficients of > the regressors are now multiplied by the standard errors of the original > regressors. > Don't you get this? > > All the best, > > Joao > > >> From "Scott Holupka" <scott.holupka@jhu.edu> >> To <statalist@hsphsun2.harvard.edu> >> Subject st: Beta values in QREG >> Date Fri, 21 Jun 2013 16:03:55 -0400 >> >> Does anyone know if there is a statistical reason why the Stata >> quantile regression program "qreg" does not provide an option for >> producing beta values? I know a question about beta values in qreg >> was raised just a few months ago, and the one response suggested that >> there might be a statistical reason why the option wasn't available, >> but I didn't see anything more definitive. >> >> I did try standardizing all of my variables and re-running QREG, as >> had been previously suggested, but the results between the >> unstandardized and standardized models seem so different I'm not sure >> if I did something wrong or if there's a more fundamental reason why the > results don't line up. > >> Thanks for any advice. >> >> Scott Holupka >> >> >> C. Scott Holupka, Ph.D. >> Senior Research Associate >> Johns Hopkins University >> Institute for Policy Studies >> 3400 N. Charles St. >> Baltimore, MD 21218-2688 >> >> 410-516-5046 >> Scott.Holupka@jhu.edu >> >> >> * >> * For searches and help try: >> * http://www.stata.com/help.cgi?search >> * http://www.stata.com/support/faqs/resources/statalist-faq/ >> * http://www.ats.ucla.edu/stat/stata/ >> >> Follow-Ups: >> Re: st: Beta values in QREG >> From: Maarten Buis <maartenlbuis@gmail.com> >> >> Prev by Date: Re: st: RE: count number of working adult Next by Date: >> RE: st: RE: count number of working adult Previous by thread: st: >> count number of working adult Next by thread: Re: st: Beta values in >> QREG >> Index(es): >> Date >> Thread >> > > * > * For searches and help try: > * http://www.stata.com/help.cgi?search > * http://www.stata.com/support/faqs/resources/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/faqs/resources/statalist-faq/ > * http://www.ats.ucla.edu/stat/stata/ > > References: > RE: st: Beta values in QREG > From: "Santos Silva, J.M.C." <jmcss@essex.ac.uk> > > Prev by Date: st: Missing daily digest? > Next by Date: Re: st: Missing daily digest? > Previous by thread: RE: st: Beta values in QREG > Next by thread: Re: st: metareg of failure rates or proportions / meta- > analysis of proportions > Index(es): > Date > Thread * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/faqs/resources/statalist-faq/ * http://www.ats.ucla.edu/stat/stata/