add -saving()- option to save the results of your bootstrap procedure,
and then analyze it in Stata using any technique you would find
useful; e.g. scatterplot of the two coefficient estimates would give
you an idea about banana-shaped confidence sets... although the formal
concept of the confidence set is quite difficult to arrive at within
the bootstrap framework for more than one dimension.
Stas
On Mon, 22 Nov 2004 17:16:30 +0000, Mark Clatworthy
<[email protected]> wrote:
> Using the following command in Stata 8:
>
> bs "reg y x1 x2" "_b[x1] _b[x2]", reps(10000)
>
> we obtain the observed coefficients, bias, se and 95% confidence interval by
> default. Although we can change the confidence interval (e.g. to 99%), we would
> ideally like to generate p-values based on the bootstrap statistics. Does
> anyone know if this can be done, and if so, how?
>
> Many thanks
>
> Mark Clatworthy
> Cardiff University
--
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/
