Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Sara Borelli <saraborelli77@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | st: stdf option after weighted regression |
Date | Thu, 26 Jul 2012 13:43:01 -0400 |
Hi all, I am running the model: reg y x adjust, by(c) stdf However when I run the same regression but weighted : reg y x [pweight=weight] adjust, by(c) stdf STATA says the stdf option is not allowed. I replicated the result of stdf after adjust for the unweighted regression using STATA manual formula: Standard error of forecast^2 = standard error of prediction^2 + variance of residual, by using standard error of prediction (se option after adjust) and the variance of residual (MSE) . I was thinking to use the same approach after weighted regression to manually compute the stdf given that the stdf option is not allowed after weighted regression. Would this be wrong? Thanks in advance for any suggestion, Sara * * 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/