Internal and external validity

When we conduct experiments, our goal is to demonstrate cause and effect relationships between the independent and dependent variables. We often try to do it in a way that enables us to make statements about people at large. How well we can do this is referred to as study�s generalisability. A study that readily allows its findings to generalise to the population at large has high external validity. To the degree that we are successful in eliminating confounding variables within the study itself is referred to as internal validity. External and internal validity are not all-or-none, black-and-white, present-or-absent dimensions of an experimental design. Validity varies along a continuum from low to high.

One major source of confounding arises from non-random patterns in the membership of participants in the study, or within groups in the study. This can affect internal and external validity in a variety of ways, none of which are necessarily predictable. It is often only after doing a great deal of work that we discover that some glitch in our procedures or some oversight has rendered our results uninterpretable.