[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
re: st: ivreg2 and panel group heteroscedasticity
Sorry, I accidentally sent the this message to Mark's personal email
From: Jeffry Jacob [mailto:email@example.com]
Sent: Saturday, August 21, 2004 2:36 PM
To: 'Mark Schaffer'
Subject: RE: st: ivreg2 and panel group heteroscedasticity
Thanks for your response. It is very helpful indeed.
Since I have a fixed effect model, I need to mean difference the data
(using dummies results in #of parameters > # groups/clusters).
My thought of _cluster_ with _bw(1)_ was motivated by the fact that
since _abar_ test indicates no autocorrelation, cluster with robust and
bandwidth(1) might give me sigma_i's for each group where _bw(1)_ will
mean no autocorrelation. But now it is clear that _cluster_ by itself
will do all this.
I have one more related question though. If there is evidence of cross
panel correlation, E(sigma_i,sigma_j)~=0, and there is endogeneity,
xtpcse can not be used. Will ivreg2 with robust give the right standard
errors in this case?
From: Mark Schaffer [mailto:M.E.Schaffer@hw.ac.uk]
Sent: Saturday, August 21, 2004 12:35 PM
To: firstname.lastname@example.org; Jeffry Jacob
Cc: Mark Schaffer
Subject: Re: st: ivreg2 and panel group heteroscedasticity
Quoting Jeffry Jacob <email@example.com>:
> Hi all,
> The latest version of ivreg2 supports panel data by requiring the
> to be tsset. But how does it interpret the _iis_ (individual
It uses it to identify the group/cluster. No fixed effects or anything
> Suppose there is no autocorrelation but group-wise
> heteroscedasticity. Does the _robust_ option give the right
> errors or they only correct for arbitrary heteroscedasticity?
> cluster option with _bw(1)_ do the trick?
Sort of. The -cluster- and -bw- options can't be used together. They
-cluster- allows for arbitrary within-group correlation (including
autocorrelation of any form). It also allows for arbitrary
heteroskedasticity, including groupwise heteroskedasticity.
-bw- allows for autocorrelation with some time structure, i.e., you
the autocorrelation to die out over time. The argument to bandwith is
related to how quickly you expect it to die out. You can combine this
with -robust- to get HAC (heteroskedastic and
> Moreover, to use _cluster_
> , I
> have to mean difference my data ( to remove individual
Strictly speaking, the answer to your question is that you can use
-cluster- without mean-differencing or otherwise transforming your data.
But it sounds like you still might want to do this anyway - it depends
the estimator you want to implement.
> As noted in Wooldridge (2002), Chapter 10, do I correct for the
> of freedom in the standard errors?
Only if you do the mean-differencing or some other transformation.
Hope this helps.
> Any response will be much appreciated.
> * 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/
Prof. Mark Schaffer
Department of Economics
School of Management & Languages
Heriot-Watt University, Edinburgh EH14 4AS
tel +44-131-451-3494 / fax +44-131-451-3008
This e-mail and any files transmitted with it are confidential
and intended solely for the use of the individual or entity to
whom it is addressed. If you are not the intended recipient
you are prohibited from using any of the information contained
in this e-mail. In such a case, please destroy all copies in
your possession and notify the sender by reply e-mail. Heriot
Watt University does not accept liability or responsibility
for changes made to this e-mail after it was sent, or for
viruses transmitted through this e-mail. Opinions, comments,
conclusions and other information in this e-mail that do not
relate to the official business of Heriot Watt University are
not endorsed by it.
* For searches and help try: