SCORE Mathematics
Definition
Confounding variables are two variables (explanatory or lurking variables) that are confounded when their effects on a response variable cannot be distinguished from each other.
Example
A soccer coach wanted to improve the team's playing ability, so he had them run two miles a day. At the same time the players decided to take vitamins. In two weeks the team was playing noticeably better, but the coach and players did not know whether it was from the running or the vitamins.
Case Study
If, for example, subjects in one group are simultaneously tested in a room with the heat set at 70 degrees whereas subjects in another group are simultaneously tested in a nearby identically appointed room with the heat set at 60 degrees, the obtained differences in performance could be attributed to any of three factors. It could be due to the random assignment of subjects (i.e. to chance). It could be due to the different temperatures in the two rooms. It could, however, be due to some confounding factor such as differences in ambient illumination that result from unnoticed differences in the orientation of each room with respect to the sun. In any experiment an appropriate statistical test can help in the decision as to whether or not to attribute the results to chance, but only the most careful analysis of the actual conditions of the experiment can suggest whether or not the result might be due to a confounding factor.