Regression discontinuity (RD) research designs identify the causal impact of a treatment using the idea that the rule governing the assignment of treatment to individuals is arbitrary. RD’s are typically used in scenarios where the treatment status of an individual (D_{i}) is a deterministic and discontinuous function of an observable characteristic (X_{i}), e.g., D_{i} =1 if X_{i}≥x_{0} and D_{i} =0 if X_{i}<x_{0}. In general, a simple regression of the form Y_{i} = f(X_{i}) + βD_{i} + u_{i} formalizes the RD set-up, where β is the causal effect of interest. The key difference between this regression and a simple OLS (discussed here) is that D_{i} is a deterministic function of X_{i}. The causal effect β is identified by distinguishing the discontinuous step-function, *1(X _{i}≥x_{0})*, from the smooth function, f(X

_{i}). It should be noted that f(X

_{i}) may or may not be linear in X

_{i}, just like an OLS set-up need not be linear in the explanatory variables, but only in the parameters.