this is known as a non-inferiority trial -- a recent article in
Statistics in Medicine talked about sample size estimation for
these studies and discussed how to use nQuery Advisor and PASS
software for this purpose: Julious, S.A. (2004), "Sample sizes
for clinical trials with normal data," 23: 1921-1986
Rich Goldstein
Steve Harvey wrote:
Dear Statalisters:
I'm having trouble with what may be a fairly basic statistics question.
I have a new intervention and want to know if the intervention is at
least as good as the standard treatment. I want to be certain that the
intervention is not poorer than the standard treatment. So...
Ho: M1 < M2
Ha: M1>= M2
If I want to be 95% certain that I can reject Ho, do I need to do
anything different in terms of calculating sample size and means testing
than under the normal Ho: M1 = M2? Do the probability distributions
under these conditions differ from those when I assume Ho: M1 = M2?
TIA,
Steve
*
* 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/
*
* 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/
