Listy Biometryczne - Biometrical Letters Vol. 34(1997), No. 2, 87-100
This paper deals with planning of experiments in partially balanced incomplete block designs with rectangular association scheme (RT PBIB). Some methods for construction of RT PBIB which can be applied to two-factor experiments are given. Incidence matrices of these designs can be obtained from Kronecjer product generalization of the selected matrices. Attention is called to statistical properties of these designs connected with the estimation of the natural and elementary treatment contrasts. Catalogue of RT PBIB designs for 6, 8, 10 and 12 tretments whose number of treatment replications r stisfies inequality 2<=r<=15 is included.
two-factorial experiments, Kronecker product of matrices, balanced matrices, RT PBIB designs