Bob said
Have you investigated the rolling procedure. This will do
rolling window regression or recursive least squares estimation. The
explication of Kit Baum's procedure in the Stata Time Series Reference
manual shows how it can do this. With it you can generate a new data set
which will reveal locations of structural breaks in your data.
To confirm the significance of such breaks, you can always use the
Chow test.
I wrote a routine rollreg (findit rollreg) somewhat before Stata 9 added the rolling prefix. I did not write their rolling code. I made some suggestions which were politely heard, but rolling does not implement the methodology I implemented in rollreg, and rolling works for all appropriate Stata commands, not just regressions. I think that for regressions my approach has some advantages, but it lacks generality (and prepaid tech support).
Kit Baum, Boston College Economics
http://ideas.repec.org/e/pba1.html
*
* 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/
