A block is a set of runs expected to be more alike than runs in different blocks: one day, one raw material lot, one chamber, one operator. Blocking assigns the design's runs to blocks in a planned way, usually confounding a high-order interaction with the block effect, so day-to-day or lot-to-lot differences are pulled out of the error term instead of inflating it. The rule of thumb is to block what you can and randomize what you cannot.
We can't do all 16 runs on one lot of wafers, so block on lot. Eight runs each, ABCD confounded with blocks.
Also heard as
- blocking
- blocking factor
Related terms
Randomization
Running experimental trials in a random order so unknown time trends and nuisance effects do not bias the results.
Confounding
Mixing of two effects so that the data cannot separate them, whether by design or through an uncontrolled variable.
DOE
Design of experiments: planning a set of runs that vary several factors at once so their effects can be separated.
Split lot
Lot of wafers divided between two or more process conditions so the comparison shares the same incoming material.