Premium
Power evaluation of small drug and vaccine experiments with binary outcomes
Author(s) -
Duchateau L.,
McDermott B.,
Rowlands G. J.
Publication year - 1998
Publication title -
statistics in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.996
H-Index - 183
eISSN - 1097-0258
pISSN - 0277-6715
DOI - 10.1002/(sici)1097-0258(19980115)17:1<111::aid-sim741>3.0.co;2-t
Subject(s) - binary number , power (physics) , drug , statistics , computer science , medicine , mathematics , pharmacology , physics , arithmetic , thermodynamics
Power analysis based on the Fisher exact test is used to evaluate the usefulness of alternative designs for small drug and vaccine experiments with a binary, success or failure, outcome. The emphasis is on the comparison between designs with equal and unequal allocations of animals to treated and control groups having the same total sample size, and between designs with equal and unequal allocations but with one or two fewer animals in the control than the treated group. Designs with unequal allocation can sometimes be more powerful at a given level of statistical significance α than designs with equal allocation. Graphs and a table are presented to aid the choice of suitable designs for (1−β)=0·80 and α=0·05. © 1998 John Wiley & Sons, Ltd.