Statalist


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

st: RE: xtreg vs. xtgls vs. xtpcse vs. xthtaylor


From   "Martin Weiss" <[email protected]>
To   <[email protected]>
Subject   st: RE: xtreg vs. xtgls vs. xtpcse vs. xthtaylor
Date   Wed, 5 Nov 2008 14:16:28 +0100

There are quite active pundits for panel data on the list, so let me just
help get -xthtaylor- out of the way: AFAIK, it does not specifically address
heteroscedasticity, but correlation between a subset of the covariates and
the individual effect u_i. 
Be careful with such posts, BTW, as they may be regarded as homework
question which are not answered on the list...

HTH
Martin

-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Fardad Zand
Sent: Wednesday, November 05, 2008 1:48 PM
To: [email protected]
Subject: st: xtreg vs. xtgls vs. xtpcse vs. xthtaylor

Dear listers,

I couldn't figure out exactly what the difference is between

(a) xtreg, vce(robust) cluster(id)
(b) xtgls
(c) xtpcse
(d)xthtaylor

To my knowledge they all try to correct some form of
heteroskedasticity or panel specific correlations. But it is not clear
to me where and when each option is best to use.

Moreover, after you run a model on panel data, how can you check:

(1) heteroskedasticity
(2) auto-correlation
(3) endogeneity
(4) multicollinearity

One probably need the above information to decide what model/estimator to
use.

I really appreciate your time and supporting me in my research.

Good luck to all of you,
Fardad

-- 
ir. Fardad Zand
Researcher & PhD Candidate
MSc Management of Technology

Department of Economics & Management of Innovation
Faculty of Technology, Policy & Management
Delft University of Technology

Kruisstraat 30
2611 MJ Delft
the Netherlands

Office: +31 15 278 42 73 (room C0.060)
Mobile: +316 54 31 57 97
Email: [email protected]
*
*   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/



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