Re: st: stcox output: p-value and CI don't agree

[Michael McCulloch <mm@pinest.org>]

> Finally, if you estimated the hazard ratio in -stcox- the header 
> would be "Observed Haz. Ratio", not "Observed coefficient".
Thank you Philip, but with all due respect I promise it's the hazard 
ratio that is returned. The following is the code I used, but for the 
purpose of this question, applied to the Stata system data file 
<cancer.dta>. Note that the plain -stcox- and bootstrapped -Cox- have 
the same effect size, but a different header.

My question is this: in the case where Cox proportional hazards 
regression results in apparently contradictory p-value and 95% CI, 
what steps would one follow to investigate this observed result?

I'd appreciate any strategy pointers that anybody might have.
Thank you!
Michael

*--------------- begin code in question -----------------------

*************
* plain cox
*************
* load data and define as survival data
sysuse cancer, clear
stset studytim, failure(died)
* run cox
stcox drug

*************
* bootstrap cox
*************
* load data and define as survival data
sysuse cancer, clear
stset studytim, failure(died)

* define program
capture program drop boot_hr
	program define boot_hr, rclass

	* cox
	stcox drug
	indeplist, local
	foreach var of varlist `X' {
		return scalar `var' = exp(_b[`var'])
	}

end 
* set seed for reproducibility, since bootstrap is a random sampling
set seed 12358

* run program
bootstrap drug=r(drug), reps(100): boot_hr
*--------------- end code in question -----------------------






*
*   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/