May occur when measurement of the dependent variable varies over time or experimental conditions.

Selection and differential attribution are the primary threats to internal validity of this design.

A potential threat to validity when subjects are selected on the basis of their extreme scores on the dependent variable.

Loss of subjects varies across experimental conditions.

Controls for the effects of history in a trend analysis by comparing a group exposed to the treatment with other groups that are not.

Randomization rules out this threat to internal validity.

This design eliminates the possibility of testing-X interaction.

Resembles the one-group pretest-posttest design except multiple observations are made before and after the treatment.

The effect of X on Y depends on Z.

A threat to internal validity when a single group is measured at two or more points in time.

An experiment in which two or more variables are manipulated.

May be confounded with the independent variable when a single group is studied over an extended period of time.