Block: A level of a random factor designated to sample unmeasured spatial or temporal variation in the environment. For example, a field that slopes north to south might be partitioned into horizontal blocks (running east-west) so that the blocking factor contains the unmeasured variation due to slope and thereby minimizes the within-block residual variation. In a randomized complete block, each level of the treatment factor (or each combination of levels in the event of two or more factors) is randomly allocated to one plot in each block. The Latin Square is a variant on this design for two blocking factors.

 

Doncaster, C. P. & Davey, A. J. H. (2007) Analysis of Variance and Covariance: How to Choose and Construct Models for the Life Sciences. Cambridge: Cambridge University Press.

http://southampton.likn.co/~cpd/anovas/datasets/