st: stcox: bootstrap option produces LOWER standard error and WIDER ci95

[Michael McCulloch <mm@pinest.org>]

I'm using stcox to estimate survival with one binary covariate (tcm), with
the model:
         stcox tcm

Perhaps I'm mistaken, but I was expecting the bootstrap option to produce a
higher standard error and wider ci95.

BOOTSTRAP       MODEL   HR     CI95             SE     p
NO                      tcm             0.77   0.36, 1.67       0.30   0.51
YES                     tcm             0.77   0.39, 1.55       0.27   0.47

Can anybody suggest why that might be the case?




Best wishes,
Michael


____________________________________

Michael McCulloch
Pine Street Clinic
Pine Street Foundation
124 Pine Street, San Anselmo, CA 94960-2674
tel     415.407.1357
fax     415.485.1065
email:  mm@pinest.org
web:    www.pinest.org
         www.pinestreetfoundation.org
         www.medepi.net/meta





*
*   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/