Universal optimality of balanced uniform crossover designs
Hedayat, A. S. ; Yang, Min
Ann. Statist., Tome 31 (2003) no. 1, p. 978-983 / Harvested from Project Euclid
Text on Project Euclid
PDF
Alt PDF
Kunert [Ann. Statist. 12 (1984) 1006-1017] proved that, in the class of repeated measurement designs based on t treatments, p=t periods and $n=\lambda t$ experimental units, a balanced uniform design is universally optimal for direct treatment effects if $t \geq 3$ and $\lambda=1$, or if $t \geq 6$ and $\lambda=2$. This result is generalized to $t \geq 3$ as long as $\lambda \leq (t-1)/2$.
Publié le : 2003-06-14
Classification:  Balanced design,  crossover design,  carryover effect,  repeated measurements,  62K05,  62K10 
@article{1056562469,
     author = {Hedayat, A. S. and Yang, Min},
     title = {Universal optimality of balanced uniform crossover designs},
     journal = {Ann. Statist.},
     volume = {31},
     number = {1},
     year = {2003},
     pages = { 978-983},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1056562469}
}

Hedayat, A. S.; Yang, Min. Universal optimality of balanced uniform crossover designs. Ann. Statist., Tome 31 (2003) no. 1, pp.  978-983. http://gdmltest.u-ga.fr/item/1056562469/