Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re: qreg versus rreg


From   "Michael Blasnik" <[email protected]>
To   <[email protected]>
Subject   st: Re: qreg versus rreg
Date   Fri, 30 Jan 2004 09:34:07 -0500

One difference between qreg and rreg is that they attempt to estimate
different versions of the central tendency -- qreg estimates the median
while rreg comes closer (in theory) to estimating a robust mean.  The
difference may be negligible in essentially symmetrical distributions, but
for skewed distributions where the mean and median are not expected to be
equal, one would expect their estimates to deviate systematically.  If you
really want to model the mean but are concerned about outliers, then rreg
may be a better choice than qreg.  If you want to model the median (or think
the underlying distribution is fairly symmetrical), then qreg may be
preferred.

I usually look at both and then try to figure out any substantive
differences in results, but I'm generally partial to the coefficient
estimates from rreg (I often deal with skewed distributions where the median
is noticeably lower than the mean).  On the other hand, I sometimes find
rreg's std errors estimates questionable.

Michael Blasnik
[email protected]


----- Original Message ----- 
From: "Richard Williams" <[email protected]>
To: <[email protected]>
Sent: Friday, January 30, 2004 8:19 AM
Subject: st: qreg versus rreg


> This came up several months ago on the list but I am still confused:  As a
> means for dealing with outliers, what are the relative merits of -rreg-
and
> -qreg-?  When should one be preferred over the other?
>
> As I understand it, -rreg- goes through this complicated weighting scheme,
> which causes outliers to be weighted less heavily.  -qreg- (by default)
> does median regression, and the median is less affected by outliers than
> the mean is.
>
> In terms of giving a quick 30 second intuitive explanation, I like
> -qreg-.  On the other hand, in the few examples I've tried myself or seen
> elsewhere, the results from -rreg- seemed more plausible.  On the other
> other hand, in those examples -rreg- basically just dropped the extreme
> outliers, and I could do that myself without a fancy program.
>
> This is one of the problems with using Stata in a stats class.  When I
only
> used SPSS, these issues never came up, because as far as I can tell SPSS
> can't do anything like this!
>
>
> -------------------------------------------
> Richard Williams, Notre Dame Dept of Sociology


*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/



© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index