Experimental Group
The experimental group is the set of subjects or samples that receives the treatment or change being tested in an experiment.
Definition
The experimental group is the part of an experiment that gets the change you are testing, with everything else the same as the control group. It is exposed to the independent variable at the level being tested, and its results are compared to the control group to measure the treatment effect; an experiment can have several experimental groups, one for each level. Members should come from the same population and follow the same procedure as the control group, differing only in the independent variable, so the between-group difference estimates the effect. Graded levels across multiple experimental groups allow a dose-response relationship to be tested.
Example
In a fertilizer test, the pot that gets fertilizer mixed into its water is the experimental group. In a salt-and-freezing investigation, three experimental groups of $100\ \text{mL}$ water hold $5\ \text{g}$, $10\ \text{g}$, and $15\ \text{g}$ of salt, each compared to the pure-water control. Testing fertilizer at $0$, $1$, $2$, and $4\ \text{g/L}$ with twelve seedlings per group gives mean heights of $10.9$, $13.2$, $14.6$, and $14.8\ \text{cm}$: the response rises then flattens, suggesting the benefit saturates near $2\ \text{g/L}$.
Key Insight
The experimental group gets exactly one thing the control group does not; give it two and the fair test is broken. Several experimental groups at different levels reveal whether an effect grows steadily or stops after a point, which a single group can never show. Sample size within the group matters as much as the treatment: three plants can give a striking mean by luck, while twelve make luck much harder to mistake for an effect.