Final answer:
A good experiment should use a control and test a single independent variable to ensure that observed changes are due to the experiment and not other factors.
Step-by-step explanation:
An essential feature of every good experiment is that it should use a control AND test a single independent variable. This ensures that the changes observed in the dependent variable are indeed due to the manipulation of the independent variable and not to other extraneous factors. By having a control group, researchers can compare the results against those of the experimental group, ensuring that any changes can be attributed to the experiment itself rather than to chance or other variables. A controlled experiment is structured such that all variables are held constant except for the independent variable, which is the only factor that should differ between the control and experimental groups.