Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: RE: st: Checking to see if the association between two variables is linear or otherwise


From   Nick Cox <njcoxstata@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: RE: st: Checking to see if the association between two variables is linear or otherwise
Date   Sat, 13 Oct 2012 16:02:08 +0100

I am sympathetic to all parties here, but the difference seems a bit
bigger than this implies. Using dummies doesn't even commit the
analyst to the idea that level of education is ordinal scale, although
my teaching career has been futile if that's not true. Using a
regression spline does seem to treat level of education, or some
transform of it, as at least interval scale.

Nick

On Sat, Oct 13, 2012 at 2:51 PM, JVerkuilen (Gmail)
<jvverkuilen@gmail.com> wrote:
> On Sat, Oct 13, 2012 at 3:20 AM, Justina Fischer <JAVFischer@gmx.de> wrote:
>> see my post to David's comment. His critique applies only if educational levels are employed as continuous variable, which I never suggested.
>>
>
> Dummies for education level bins is essentially a zero-order spline
> and so a regression spline gives a way to compromise between the
> "wiggly" regression implied by dummies and the overly smooth one
> represented by a linear term, so the choice isn't really an either/or.
*
*   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/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index