Term: Regression Discontinuity Design (RDD)

Glossary Definition

Last Updated: 2007-12-12

Definition:

Quasi-experimental, pretest-posttest control group design that is characterized by its unique method of assignment to intervention: participants are assigned to either the intervention group or control group solely on the basis of a cut-off score on a pretest measure. The RDD is so named because a regression line is plotted to relate the assignment and outcome variables. If the treatment is effective, a discontinuity in the regression line should occur at the cutoff point. By comparison, the absence of a discontinuity is interpreted as a null effect.

References 

• Brownell M, Santos R, Kozyrskyj A, Roos N, Au W, Dik N, Chartier M, Girard D, Ekuma O, Sirski M, Tonn N, Schultz J. Next Steps in the Provincial Evaluation of the BabyFirst Program: Measuring Early Impacts on Outcomes Associated with Child Maltreatment. Winnipeg, MB: Manitoba Centre for Health Policy, 2007. [Report] [Summary] (View)