Detection of a Treatment Effect When Not All Experimental Subjects Will Respond to Treatment

Publisher Website
Google Scholar
Abstract
Non-responders attenuate average response and inflate sample variance, reducing the power of standard parametric tests. A new Fisher''s type randomization test, which has no parametric analog, is recommended when not all subjects may be capable of responding to treatment. The new test was evaluated by Monte Carlo means and applied to drug abuse data and to virus titer data. In most trial applications the new test was more sensitive to treatment effects than the Student''s test.

This publication has 0 references indexed in Scilit: