Treatment and control groups
In the design of experiments, treatments are applied to experimental units in the treatment group(s). In comparative experiments, members of the complementary group, the control group, receive either no treatment or a standard treatment.
A placebo control group can be used to support a double-blind study, where a portion of patients are given a placebo medication (typically, sugar pill), in order to observe the patients are taking their medications in the manner as proscribed, with no major procedural differences between the treatment group(s) versus the placebo control group(s). In such cases, a 3rd, nontreatment control group can be used to measure the placebo effect, as the difference between placebo subjects and the non-treatment subjects, perhaps paired by age group, twin/triplet or other related factors.
For the conclusions drawn from the results of an experiment to have validity, it is essential that the items or patients assigned to treatment and control groups be representative of the same population. In some experiments, such as many in agriculture or psychology, this can be achieved by randomly assigning items from a common population to one of the treatment and control groups. In studies of twins involving just one treatment group and a control group, it is statistically efficient to do this random assignment separately for each pair of twins, so that one is in the treatment group and one in the control group.
In some medical studies, where it may be unethical not to treat patients who present with symptoms, controls may be given a standard treatment, rather than no treatment at all. An alternative is to select controls from a wider population, provided that this population is well-defined and that those presenting with symptoms at the clinic are representative of those in the wider population. Another method to reduce ethical concerns would be to test early-onset symptoms, with enough time later to offer real treatments to the control subjects, and let those subjects know the first treatments are "experimental" and might not be as effective as later treatments, again with the understanding there would be ample time to try other remedies.
- Hinkelmann, Klaus; Kempthorne, Oscar (2008). Design and Analysis of Experiments, Volume I: Introduction to Experimental Design (2nd ed.). Wiley. ISBN 978-0-471-72756-9. MR 2363107.
- Bailey, R. A. (2008). Design of comparative experiments. Cambridge University Press. ISBN 978-0-521-68357-9. MR 2422352.
- Seeley, Ellen W.; Grinspoon, Steven - Harvard Medical School. "Chapter 2: Patient-Oriented Research". Clinical and Translational Science: Principles of Human Research. edited by David Robertson, Gordon H. Williams. p. 13, parag. 3 under "Clinical Trials". associated "healthier choices" and "nontreatment group". Retrieved 2018-07-30.
- Chaplin S (2006). "The placebo response: an important part of treatment". Prescriber: 16–22. doi:10.1002/psb.344.
- Everitt, B.S. (2002) The Cambridge Dictionary of Statistics, CUP. ISBN 0-521-81099-X (entry for control group)
- Neyman, Jerzy (1990) , Dabrowska, Dorota M.; Speed, Terence P., eds., "On the application of probability theory to agricultural experiments: Essay on principles (Section 9)", Statistical Science, 5 (4): 465–472, doi:10.1214/ss/1177012031, MR 1092986
- Ian Hacking (September 1988). "Telepathy: Origins of Randomization in Experimental Design". Isis (A Special Issue on Artifact and Experiment). 79 (3): 427–451. doi:10.1086/354775.
- Stephen M. Stigler (November 1992). "A Historical View of Statistical Concepts in Psychology and Educational Research". American Journal of Education. 101 (1): 60–70. doi:10.1086/444032.
- Trudy Dehue (December 1997). "Deception, Efficiency, and Random Groups: Psychology and the Gradual Origination of the Random Group Design". Isis. 88 (4): 653–673. doi:10.1086/383850. PMID 9519574.
|This statistics-related article is a stub. You can help Wikipedia by expanding it.|