Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Sportökonomie <sportoekonomie@gmx.de> |
To | statalist@hsphsun2.harvard.edu |
Subject | Re: st: xtivreg, re: Autocorrelation & heteroscedasticity |
Date | Tue, 12 Nov 2013 23:32:56 +0100 |
Dear Sergiy,thanks for your response. I used the xtgls command as suggested in your link, while I was not controlling for endogeneity. However, I found out that I have to control for endogeneity and followed the suggestion to do this with Balestra & Varadharajan-Krishnakumar's (1987) 2SLS model with the xtivreg command.
So I can either control for endogeneity with the xtivreg command or I control for autocorrelation and heteroscedasticity with the xtgls command. However, I would like to control for all three options simultaneously.
Is there a command or workaround that is capable to do this? Did I misunderstand anything?
Thanks, Marc Am 12.11.2013 22:37, schrieb Sergiy Radyakin:
Marc, see here: http://www.stata.com/support/faqs/statistics/panel-level-heteroskedasticity-and-autocorrelation/ Best, Sergiy On Tue, Nov 12, 2013 at 4:10 PM, Sportökonomie <sportoekonomie@gmx.de> wrote:Dear Statalist, I am working with a random effects panel regression including 200+ observations. My model does also include instrumental variables (xtivreg, re). How can I (a) test, and (b) adjust my model for autocorrelation and heteroscedasticity? Thanks in advance, Marc * * 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/
* * 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/