Confounding
Two
variables are confounded if they
vary together in such a way that it is impossible to determine which
variable is responsible for an observed effect. For example, consider
an experiment in which two treatments for depression were compared.
Treatment one was given to teenaged girls and treatment two was given
to middle age women. If a difference between treatments were found,
it would be impossible to tell if one treatment were more effective
than the other or if treatments for depression are more effective for
one age group than the other. Age and treatment are confounded.
Naturally, no competent experimenter would design an experiment like
that. However, some confounding is much more subtle. An experimenter
may accidentally manipulate a variable in addition to the variable of
interest.