Statalist The Stata Listserver

[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: Robust regression for outliers in panel data

From   "Nick Cox" <>
To   <>
Subject   st: RE: Robust regression for outliers in panel data
Date   Thu, 20 Jul 2006 15:29:23 +0100

In my view, although that naturally does not implicate
StataCorp, -rreg- is something of a historical
hangover, implementing as it does a particular
approach documented in one particular paper in  
1985. Not that it does not seem smart, sensible
and so forth: the problem is that there are dozens
of ways of doing robust regression that also appear
smart, sensible and so forth, at least to outsiders
to robust statistics, and how is StataCorp supposed
to choose which ones should be dignified with 
implementation within official Stata? 

Anyway, it would seem most unlikely that anyone would
want to build on it by adding -xt- elements. In any 
event, apparently no one has. It would seem much more
likely that someone would want to build -xtqreg-. 

I suspect the best thing for you to do is to 
robustify or otherwise check your analysis outside 
any -xt- framework, for example by exploring variable 
transformations, prior Winsoring, etc. and comparing 
the results with -xtreg- and different "versions" of
your data. 


Johanna Vogel
> I am trying to carry out panel data regressions 
> (specifically, fixed effects, Arellano-Bond first-differenced 
> and system GMM estimators) that are robust to outliers. Does 
> a Stata command exist in the panel data context (I am not 
> sure if "rreg" applies in the xt-case)? If not, are there 
> other ways to arrive at the same result?

*   For searches and help try:

© Copyright 1996–2021 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index