Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: Quantile regression
From
"JVerkuilen (Gmail)" <[email protected]>
To
[email protected]
Subject
Re: st: Quantile regression
Date
Sat, 22 Sep 2012 10:40:26 -0400
On Sat, Sep 22, 2012 at 10:33 AM, Nick Cox <[email protected]> wrote:
> The choice need not seem so stark. With a link function approach, as
> with -poisson- or -glm, link(log)-, you can fit on a log scale and
> report on the original scale. I would guess that this would make most
> sense to clinicians and patients alike in this example.
Ah I certainly didn't mean to make it look that way. Yes a gamma GLM
with log link is also a very good choice. What I like about quantile
regression is that as long as it's assumptions are reasonably met,
it's relatively immune to choices of the exact distribution. But it
can be tricky to interpret.
--
JVVerkuilen, PhD
[email protected]
"Out beyond ideas of wrong-doing and right-doing there is a field.
I'll meet you there. When the soul lies down in that grass the world
is too full to talk about." ---Rumi
*
* 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/