Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at

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

Re: st: RE: xtreg check for outliers

From   Dalhia <>
To   "" <>
Subject   Re: st: RE: xtreg check for outliers
Date   Thu, 9 Aug 2012 00:42:57 -0700 (PDT)

Thanks David and Dave, this is very helpful. Will try what you suggested.

----- Original Message -----
From: "Jacobs, David" <>
To: "''" <>
Sent: Wednesday, August 8, 2012 3:40 PM
Subject: st: RE: xtreg check for outliers

An easier way would be to create the case dummies using i.your-case-id-variable and use regress.  

Then you will have access to all of the regression diagnostics in Stata.  Stata's regression is quick and there's no reason (subject to matrix constraints limited by your machine's memory) why -regress- could not handle quite large numbers of explanatory variables created by the addition of many case dummy variables.  The standard errors will be slightly off, but the point estimates will be the same as those provided by dedicated fixed effects estimators.

Dave Jacobs

-----Original Message-----
From: [] On Behalf Of Dalhia
Sent: Wednesday, August 08, 2012 7:05 AM
Subject: st: xtreg check for outliers


How do I check for outliers when using xtreg, fe? One solution I thought of was to demean each variable for each panel, and then rerun using regress, and then use the cook's d, dfits, avplot etc. 
to identify outliers. Is this a reasonable solution? Is there a different/better way to do this?

*   For searches and help try:

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index