Discusses how blocking is used in experimental design, and how the design affects how we analyze the data. In randomized complete blocks designs, the treatment comparisons are the primary interest, whereas the blocking variable is usually only of interest as a means to improve the precision of the treatment comparisons. In some situations blocking is unavoidable, e.g., when comparing several annealing treatments when only a certain number of runs can be done at the same time. More specialized blocking designs are discussed, such as incomplete block designs where only a subset of treatments fit into each block.