Treatments are often assessed in small experimental units to economize
on resources. Treatment differences for the large units used in pract
ice may then be poorly estimated because of interference. Using prior
information on treatments, designs are proposed which control interfer
ence by ensuring that treatments in neighboring units are similar. Int
erference may then be ignored in the analysis. Two types of designs ar
e considered: block designs which are based on the concurrence of trea
tments in the same block, and neighbor designs which take account of t
he concurrence of treatments in adjacent units.