| Part of a series on the|
Philosophy of science
An experimental control, often referred to as a "control group", is a population or set of objects that is statistically similar to the set being tested, on which no changes are implemented. In psychology and biology, the control group is very important, since results are often statistical rather than concrete. For instance, in testing a drug for a malady, some percentage of the test subjects will heal with no intervention (or heal at some rate in a third group, people getting an existing remedy). The control group yields this number, and the group getting the treatment under test can be compared to this to determine efficacy. While it is less of an issue in the physical sciences, part of the description of how to set up an appropriate experiment should always address what controls are used to limit the independent variables to the one of concern.
A control group's purpose is to make sure that any observed results are statistically related to the tests being performed, and not simply random occurrences that happen anyway. A good control group has subjects that, in every important way, resemble the experimental group, except for the difference in the experimental condition. In the case of animal studies, a control group may be siblings or twins of the experimental animals. Human medical trials often form a control group using random assignment. In some cases, these trials have multiple control arms, in order to test combinations of several treatments or to compare differing doses. These arms can be control groups for some comparisons and experimental groups for other comparisons. In order to assure that the carrier of a substance being tested is not having an effect, sometimes the control group will receive a saline injection (in the case of injection drugs) or be put in an inhalation chamber (e.g., in the case of rodent toxicology studies on gases); these are known as vehicle controls.