Designing a Biological Experiment: Units, Controls and Randomisation
Before any measurement is taken, the design fixes what can be concluded: what the experimental unit is, what varies with it, and what is held fixed or randomised. This stop writes the design down while the data do not yet exist.
What a learner can do afterwards
- Identify the experimental unit in a stated protocol and count it correctly
- Choose blocking or randomisation for a stated nuisance factor and justify the choice
- Name the control that rules out the alternative explanation a reviewer will raise first
1 · Read
You write the design before any measurement exists. You name the treatments, the units that receive them, and the response to measure. The experimental unit is the smallest thing independently assigned, and miscounting it is the classic error.
You defend the causal claim with two tools. Controls receive everything except the active factor, so any gap traces back to the treatment. Random assignment spreads unknown differences evenly, and replication across many units shrinks the role of luck.
You test a feed additive on trays of twenty plants with one tray per dose. You refuse to call it n equals twenty per group, because the tray was assigned, not the plant. You average each tray to one value, then compare trays.
You match the layout to the nuisance you fear most. You block a known nuisance like clinic or batch by grouping similar units first and randomizing inside blocks. And you never confuse assignment with sampling: assignment defends the causal claim inside, sampling defends generalization outside.
You name the unit, you control and randomize, you block known nuisances, and you count only independent units.
2 · Watch
Take it off screen
Where it sits
Where this leads
8 questions wait behind this lesson, each with its answer explained. Every answer feeds the sky: stars light as they are learned, and dim when it is time to come back.