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
Vasan Kandaswamy <[email protected]>
To
"[email protected]" <[email protected]>
Subject
RE: st: Quantile regression
Date
Sat, 22 Sep 2012 20:09:28 +0000
Thank you Nick, JVerkuilen , David and all others for your suggestions and help.
I am working as suggested and would get back in case I am stuck.
Thanks for making it explicit and easy.
Best regards,
Vasan
________________________________________
From: [email protected] [[email protected]] on behalf of Nick Cox [[email protected]]
Sent: Saturday, September 22, 2012 4:33 PM
To: [email protected]
Subject: Re: st: Quantile regression
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.
Nick
On Sat, Sep 22, 2012 at 2:09 PM, JVerkuilen (Gmail)
<[email protected]> wrote:
> Ah one more point:
>
> As to whether you use log(glucose) or glucose depends on the
> literature and what is a meaningful outcome. I cannot answer that, as
> this is really not my field, but one nice thing about quantile
> regression is that it has some nice invariance properties to monotone
> transformations of the dependent variable.
*
* 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/
*
* 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/