On Tue, Feb 12, 2013 at 10:51 AM, Nick Cox <njcoxstata@gmail.com> wrote:
> Some of this is textbook stuff but a standard if not universal line is
> that linearity is the most important assumption of the linear model.
>
> I'd like to repeat my advice that residual vs fitted plots are the
> best general guide to whether the pattern of residuals is
> satisfactory.
Nick you wrote something on regression diagnostic plots but I can't
recall where I saw it.
*
* 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/
