Main Principles of experimental design: the 3 “R’s”

There are three basic principles behind any experimental design:

Randomisation: the random allocation of treatments to the experimental units.

Randomize to avoid confounding between treatment effects and other unknown effects.

Replication: the repetition of a treatment within an experiment allows:

To quantify the natural variation between experimental units.

To increase accuracy of estimated effects.

Reduce noise: by controlling as much as possible the conditions in the experiment. A classical example is the grouping of similar experimental units in blocks.

Using known characteristics/properties of the experimental units to explain variation, for example inclusion of block effects in the statistical model.