Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | "Nick Cox" <n.j.cox@durham.ac.uk> |
To | <statalist@hsphsun2.harvard.edu> |
Subject | st: RE: non-normal residual |
Date | Thu, 29 Apr 2010 18:40:07 +0100 |
At most, it may be assumed that (*) errors are distributed normally. However, this is the least important assumption for most statistical purposes. No flavour of a standard linear model assumes that the response is distributed normally. It's pretty much diagnostic of lousy textbooks or articles if they say this. If (*) is true, then it is to expected that residuals will be distributed approximately normally. This much should be conveyed, and more precisely, by any decent text. It is not easy to give good advice on what you should do. It's not out of the question that your model is fine, or as good as could be done. But I would spend much more time looking at the residual vs fitted plot than at the distribution of residuals. Nick n.j.cox@durham.ac.uk Fabio Zona I have a cross-section multiple regression: however, - Y is not distributed normally (some say it should be; some say it is not needed! where is the truth? I read residuals must be normally distributed, not the Y...) - any tranformation of Y does not allow to approach a normal-distribution - beyond Y, residuals are non-normally distributed Any suggestions on how to handle this situation? * * 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/