Thanks to all for their input on this topic. I have a time series of inflation,
interest rate, output and so on. I have searched recent literature and what I
had in mind is what Inoue and Shintani propose in the following paper.
Bootstrapping GMM Estimators for Time Series by Inoue and Shintani, 2004,
Journal of Econometrics, forthcoming (for those who are interested a discussion
paper version is available on the author's webpage).
After reading all suggestions and the manual, I don't think Stata can do such
estimation at present.
Thanks
Vidya
>>> [email protected] 30/09/04 9:37 PM >>>
The relatively commonly accepted way to do the time series bootstrap
is by blocks. If what you indeed have are panel data, then I would
suggest resampling by panels as a whole. You should be able to do that
with -bootstrap, cluster()-. If yours is a genuine time series, you
need to find out what the state of the art is through current
publications on the topic. It's going to be tough to taylor Stata's
-bootstrap- to work with that, however.
Stas
On Thu, 30 Sep 2004 19:57:12 +0100, Vidya Mahambare
<[email protected]> wrote:
> Jeff, Thanks for pointing out that -bootstrap - in Stata is not appropriate
for
> time series data. Is there an inbuilt way in Stata to do time series
> bootstrapping?
>
> Vidya
>
> Dr Vidya Mahambare
> B21, Cardiff Business School
> Ph: 0044 29 2087 6407
--
Stas Kolenikov
http://stas.kolenikov.name
*
* 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/
*
* 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/
