2 July 2020 - The method is used to study the outcomes related to an abrupt change when it is not possible to randomly assign patients to the conditions before and after the change. 

A goal of an regression discontinuity design is to minimise the effect of confounding on the estimated effect of a policy or treatment change.

Unobserved confounding is particularly concerning in non-randomised studies because this bias cannot be completely removed using conventional statistical methods, such as regression or propensity score–based analysis.

Read JAMA Guide to Statistics and Methods