st: xtivreg and clustered bootstrap

[John Antonakis <john.antonakis@unil.ch>]

Hi:

I am estimating an iv model that has random effects (as tested by 
-xttest0-) and whose coefficients do not differ from a fixed-effects 
model (as tested by -xtoverid-). 

I would like to use the bootstrap to ensure that my standard errors are 
consistent given possible common "firm" and "year" shocks.  I have 
strongly balanced panel data. I am not sure about which order to add in 
the firm and year clusters. Is the right command:

set seed 100
bootstrap, cluster(firm year): xtivreg y (x1 x2 = z1 z2 z3) c1 c2 c3

I have tried with the option cluster (year firm) too and I get similar 
standard errors (but not the same one, as I guess the sample frame is 
different).

Which is the best way to go?

Thanks,
John.

--
____________________________________________________

Prof. John Antonakis, Associate Dean 
Faculty of Business and Economics
Department of Organizational Behavior
University of Lausanne
Internef #618
CH-1015 Lausanne-Dorigny
Switzerland

Tel ++41 (0)21 692-3438
Fax ++41 (0)21 692-3305

Faculty page:
http://www.hec.unil.ch/people/jantonakis

Personal page:
http://www.hec.unil.ch/jantonakis
____________________________________________________

*
*   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/