Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: equivalence trial power calculation

From   "Jannik Helweg-Larsen" <[email protected]>
To   <[email protected]>
Subject   Re: st: equivalence trial power calculation
Date   Wed, 8 Oct 2003 21:42:38 +0200

Many thanks to John Moran, Constantine Daskalakis and Paul Seed for their
very insightful and useful answers

sorry if I perhaps did pose my original question inaccurately-

My original aim was actually to understand the power calculations behind the
following paper:Abacavir-lamivudine-zidovudine vs
indinavir-lamivudine-zidovudine in antiretroviral-naive HIV-infected adults:
A randomized equivalence trial.Staszewski S et al, JAMA 2001 Mar
7;285(9):1155-63, - in which  they state (quote:) "The study was powered to
assess treatment equivalence for the primary end point (ie, a plasma HIV RNA
level of 400 copies/mL at week 48 for the intent-to-treat population). For
the primary end point, treatments were considered equivalent if the 95%
confidence interval (CI) was within the bound of -12% to 12%. As a result of
discussions with clinical investigators and with the Food and Drug
Administration, the margin for equivalence was preselected as the largest
difference that would be considered clinically acceptable.25 Based on these
parameters, the study was designed to enroll approximately 550 patients,
with 275 in each treatment group..."

Following this I was interested in calculating the power in a hypothetical
study of HIV-treatment assuming a yearly rate of 3.5 % virologic failures
with the "standard treatment". Concerning the bound of 12%, recent similar
HIV trials have chosen   figures in the range of 10-15%..

As a follow up, for other interested - I found a few other good references

Points to consider on switching between superiority and non-inferiority.
Available at:

Scientific and Ethical Issues in Equivalence Trials
Benjamin Djulbegovic and Mike Clarke,JAMA. 2001;285:1206-1208

in addition there is a useful ado in this statalist message: with a
correction in

thanks again


*   For searches and help try:

© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index