Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "Anat (Manes) Tchetchik" <anatmanes@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: xtivreg2 with factor variables |
Date | Tue, 31 Dec 2013 13:31:20 +0200 |
David, thanks for your advice, as for your question: I used -xtivreg2- model for its ability to accommodate two-way cluster-robust covariance matrix estimates (i.e. country and year). I have no instruments in the model, I used lagged independent variables. As I understand that using iv is an option in the -xtivreg2- not mandatory (also, if if matters, my data is not consistent with re estimation only fe). I'm not sure I understand what do you mean by "treat year as continuous" . as I understand it years can be either represented in one categorical variable, or several binay vars. (dummies) Best regards, Anat On Tue, Dec 31, 2013 at 12:34 AM, David Torres <writeon4truth2@msn.com> wrote: > > Anat, > > Try the xi: operator before the command. > > xi: xtivreg2 log_ss dem gini gdp i.year, fe cluster(country_code year) bw(1) > > That will automatically break year out into dummy variables. > > I'm surprised, though, that you're using -xtivreg2- in the absence of any instruments. I would argue that if you want to treat year as continuous, you should rethink the model. You might also prefer using -xtivreg- over -xtivreg2-. For instance, say you need to instrument for one of the variables in your model, say gdp. Let's give the instrument a generic name, say rainfall. You would do something like this: > > xtivreg log_ss dem gini c.year (gdp = rainfall), re vce(cluster country_code) > > and interactions are also possible: > > xtivreg log_ss dem gini gini#c.year (gdp = rainfall), re vce(cluster country_code) > > The last model here assumes gini is a time-invariant predictor for which you want to know its relationship to time. > > Cheers, > > -- > > David Diego Torres, PhD > NSF SBE Postdoctoral Research Fellow > Houston Education Research Consortium > Rice University > 6100 Main Street, MS-28 > Houston, TX 77005 > Phone: 713-348-2984 > Email: ddtorres at rice dot edu > > > ---------------------------------------- > > Date: Tue, 31 Dec 2013 00:15:11 +0200 > > Subject: st: xtivreg2 with factor variables > > From: anatmanes@gmail.com > > To: statalist@hsphsun2.harvard.edu > > > > Dear all, > > I have an unbalanced panel of macroeconomic data on 35 countries over 17 years. > > My analysis shows that time effects are jointly significant, as well > > as indicated first order autocorrelation. > > I > > therefore ran the following command: > > . xtivreg2 log_ss dem gini gdp i.year, fe cluster(country_code year) bw(1) > > > > I got the following error: factor variables not allowed > > Shell I specify each year dummy (excl. one) or is there a different > > problem here? > > Any advise will be appreciated! > > Anat > > > > > > -- > > Anat Tchetchik, PhD > > Department of Business Administration > > Guilford Glazer Faculty of Business and Management > > Ben-Gurion University of the Negev > > P.O.Box: 653 > > Beer-Sheva, Israel, 84105 > > > > E-mail: anat@som.bgu.ac.il > > Phone 972-(0)8-6479735 > > Fax: 972-(0)8-6472920 > > * > > * 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/ -- Anat Tchetchik, PhD Department of Business Administration Guilford Glazer Faculty of Business and Management Ben-Gurion University of the Negev P.O.Box: 653 Beer-Sheva, Israel, 84105 E-mail: anat@som.bgu.ac.il Phone 972-(0)8-6479735 Fax: 972-(0)8-6472920 * * 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/