Abstract
A balanced incomplete block design (BIBD) is instrumental in design of experiments. This is usually constructed by algebraic methods such as finite algebra or difference sets. However, in algebraic approaches, no unified method exists, and each BIBD has been constructed in some ad hoc ways. On the other hand, computer-based methods apply the same algorithm to all BIBDs; hence, these are unified approaches. Although various meta-heuristic algorithms have been tried, the success of these methods has been rather limited. This article presents an alternative approach to this problem that formulates the problem as a nonlinear mixed integer programming problem. We develop a branch-and-bound algorithm to solve this, and a tabu search algorithm to overcome some weakness in the former algorithm. We compare the performance of these algorithms against some previously developed algorithms, and demonstrate that our algorithms are competitive to these methods.
Acknowledgements
The authors are grateful to two anonymous referees for their constructive criticisms and suggestions, which improved the exposition of the paper significantly.