Threats to the Internal Validity of a Study

Results in Differences Within or Between Individuals

· Maturation--Changes in the dependent variable may be due to biological or psychological processes.

· Selection--Differences between groups may be due to differential selection or assignment to groups.

· Selection by Maturation Interaction--Similar to selection, but the main focus is the maturation of the participants.

· Statistical Regression--Changes in the dependent variable may be due to the movement of an attribute to the mean of that attribute.

· Mortality--Differences between groups may be due to a differential loss of participants.

· Instrumentation--Changes in the dependent variable may be due to changes in how the dependent variable is measured.

· Testing--Changes in the dependent variable may be due to the effect of the first testing on the second.

· History--Changes in the dependent variable may be due to events other than the independent variable that occur between the first and second measurement or during the application of the independent variable.

· Resentful Demoralization of the Control Group--Differences between groups may be inflated due to a lack of effort on the part of the control group.


Results in Similarities Within or Between Individuals

· Diffusion of Treatment--Differences between or within groups may be decreased due to unintended exposure to the independent variable.

· Compensatory Rivalry by the Control Group--Differences between groups may be decreased due to increased effort on the part of the control group to keep pace with the experimental group.

· Compensatory Equalization of Treatments--Differences between groups may be decreased due to unintended compensation of the control group for not receiving the independent variable.

Top