Threats to internal validity consist of categories of extraneous variables that may be confounded with the independent variable.

Pretesting or measuring subjects twice in the same study controls for testing effects.

The use of a nonprobability sample makes selection a threat to internal validity.

Pre-experimental designs lack one or more features of a true experiment.

True experimental designs control for threats to internal validity.

In social research, within-subject designs are preferable to between-subject designs.

The external validity of true experimental designs may be limited by the interaction of the independent variable with some other feature of the experiment.

An interaction effect occurs when the effect of one independent variable depends on the level of another variable.

Quasi-experimental designs contain all the features of a true experiment except the manipulation of the independent variable.

One potential threat to the internal validity of time-series designs is instrumentation.