In the context of threats to internal validity, differential regression is said to exist when more than one group is involved in a study and the attrition across the groups is not comparable.

Differential Regression

A statistical phenomenon where groups with extreme scores on a pretest will likely have less extreme scores on a posttest, not due to the intervention but to statistical artifacts.

Internal Validity

refers to the degree to which a study accurately establishes cause-and-effect relationships free from confounding variables.

Attrition

Attrition refers to the reduction in the number of participants or subjects over the course of a study, which can affect the study's outcomes and generalizability.