Home > Working Scientifically > Experimental Design > Control Group

A change in the independent variable could result in a change in the dependent variable, but a change in the dependent variable could also be the result of a random variable which may find its way into the experiment. 

To ensure that this does not happen, a controlled experiment is run. 

• A control group is an additional experimental run or treatment. 
• It is a separate experiment, set up like the others with exactly the same conditions. 
• The only difference is that test variable is changed.

In an experiment, a control is a treatment which is included to provide a reference set of data which can be compared with data obtained from the experimental treatments. 

Dependable controls are sometimes hard to develop. Without a control you cannot be sure that changing the variable causes the observations seen. 

For example, an investigation into the effect of increased copper in the soil on plant growth would have as a control a group of plants grown in copper free growth medium (soil). The effect of copper can be determined by comparing the growth rates of plants in growth medium with various levels of copper with the control. For this comparison to be valid, it is critical there are no other variables apart from the independent variable that differs between the control and experimental groups.

In the example below click "Grow" to grow a control plant, or grow experimental plants with different concentrations of copper in the soil. 

  Examples

Working Scientifically
Observations
Observation Questions
Hypothesis Formation
Experimental Design
Aspects
Ethics
Types of Research
Data Analysis