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 on April 23, and its replacement, statalist.org is already up and running.


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

Re: st: standardized beta for quantile regression


From   "JVerkuilen (Gmail)" <jvverkuilen@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: standardized beta for quantile regression
Date   Thu, 20 Sep 2012 22:57:54 -0400

On Thu, Sep 20, 2012 at 3:16 PM, Vasan Kandaswamy
<vasan.kandaswamy@ki.se> wrote:
> Dear Statalisters,
>
> I did a quartile regression of various predictors and outcome variables. Now I would like to estimate the relative strength of the various predictors within this model using standardized beta.

<snip>

> Kindly tell me how to estimate standardized beta in a quantile regression?
> Sugggestions of any sort will be of great help.

It's hardly surprising that adding beta as an option doesn't work as
-qreg- doesn't have such an option. See the help or the dialog box.
(IMO the dialog boxes are the first line of defense help feature. I've
been using Stata heavily for four versions and still like it as a
refresher/quick summary about what options exist for a given
procedure.)

When a Stata procedure does't have a feature it is often (but not
always) a sign that the feature is dubious for the procedure in
question. I'm not entirely sure it standardized betas even makes sense
for quantile regression, but you can always standardize all the
variables and rerun the quantile regression, though the interpretation
won't really line up the same the way it does in linear regression, I
don't think.
*
*   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/


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