Activity Number:
|
92
|
Type:
|
Topic Contributed
|
Date/Time:
|
Monday, August 12, 2002 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Biopharmaceutical Section*
|
Abstract - #301149 |
Title:
|
A Nonparametric Procedure for the Analysis of Balanced Crossover Designs
|
Author(s):
|
Francois Bellavance*+ and Serge Tardif and Constance van Eeden
|
Affiliation(s):
|
HEC Montreal and Université de Montréal and University of British Columbia
|
Address:
|
3000 chemin de la Cote-Sainte-Catherine, Montreal, Quebec, H3T 2A7, Canada
|
Keywords:
|
Permutation tests ; crossover designs ; balanced designs
|
Abstract:
|
Nonparametric tests will be presented for the hypotheses of no-direct treatment and carryover effects for balanced M-period M-treatment crossover designs. The design consists of n replicates of balanced crossover designs. The tests are permutation tests based on the n vectors of least squares estimators of the parameter of interest obtained from the n replications of the experiment. The exact, as well as the asymptotic, distribution of the test statistics are obtained, and it is shown that the tests have, asymptotically, the same power as the F-ratio test.
|