24.7 Steps for Sharp RD
Graph the data by computing the average value of the outcome variable over a set of bins (large enough to see a smooth graph, and small enough to make the jump around the cutoff clear).
Run regression on both sides of the cutoff to get the treatment effect
Robustness checks:
Assess possible jumps in other variables around the cutoff
Hypothesis testing for bunching
Placebo tests
Varying bandwidth