On 26 DF�mh 2005, at 16:34, Vivian Goodell wrote:
Don't know if this would help, but we do PASS calcs for new tumor
markers like this: Set power and alpha at something reasonable
(reasonable to review boards, usually 80% and 0.05)and create a graph
showing a range of sample sizes plotted against a range of effect
sizes.
As a member of a review board, running a study that has a 20% chance
of failing to find a clinically important effect, if such an effect
exists, is no longer acceptable. We like to see 90% or even 95% power
reported. I encourage people I work with to report both. The problem
in medical research (and in other areas too, I guess) is false
negative findings.
Ron�n Conroy
[email protected]
*
* 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/
