24.8 Steps for Fuzzy 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).
Graph the probability of treatment
Estimate the treatment effect using 2SLS
Robustness checks:
Assess possible jumps in other variables around the cutoff
Hypothesis testing for bunching
Placebo tests
Varying bandwidth