Search

Incomplete block designs bring out useful information from agricultural experimentation with high precision when there is a crunch in resources in terms of homogeneous blocks that can accommodate all the treatments. Balanced incomplete block designs or 2-designs are the most popular class of incomplete block designs. t-designs represent a generalized class of balanced incomplete block designs in which the number of blocks in which any t treatments (t≥2) occur together is a constant. In order to obtain tbalance, we may require large number of blocks and replications. Partially balanced t-designs are introduced for experimental situations where it is not possible to get balanced t-designs. Two series of such designs are obtained using cyclic development of initial block(s). Association of the proposed designs with t-packing designs are also demonstrated. [ABSTRACT FROM AUTHOR]

Kronecker product of matrices can be advantageously used to obtain three-associate class partially balanced incomplete block (PBIB) designs from two-associate class PBIB designs, for a larger number of treatments. This method has been described here and two such series of PBIB designs are obtained. If the experimenter is constrained of resources, theses designs can be used as an alternative to balanced incomplete block designs or 2-associate class partially balanced incomplete block designs. [ABSTRACT FROM AUTHOR]

In this paper, a new series of incomplete block designs with three replications has been proposed. These designs are partially variance balanced following a group divisible association scheme. The designs obtained here are with unequal block sizes and are suitable for experimentation in uneven land. Furthermore, these designs are resolvable, which enhances their application potential in regions where it may be difficult to accommodate complete replications at one place. [ABSTRACT FROM AUTHOR]