In a scientific experiment, extraneous variables are those conditions other than the one the scientist controls that cause any effect on the outcome of the experiment. Researchers attempt to minimize the effects of these extraneous variables by keeping them the same in each group they test. The scientist attempts to keep records of any variables, such as accidents, that are out of his control.
Every experiment includes extraneous variables. In the lab, one method of controlling extraneous variables is placing the control group side by side with the experimental group. When an experiment does not give the expected results, further study often reveals an extraneous variable, the scientist did not initially consider, is responsible.
Extraneous variables become more difficult to control with human subjects. The participants have different genetics and life experiences. Scientists attempt to eliminate variables by studying large groups of people and by using statistical analysis of the resulting data. Drug manufacturers use this approach in testing the efficacy of a new medication. Research by Campbell and Stanley indicates at least eight types of extraneous variables: history, maturation, testing, instrumentation, selection, statistical regression, attrition or experimental mortality and selection interaction effects. Extraneous variables are often factors when scientists publish conflicting studies.