An Empirical Evaluation of the Impact of New York's Bail Reform on Crime Using Synthetic Controls

Code for An Empirical Evaluation of the Impact of New York's Bail Reform on Crime Using Synthetic Controls.

Dependencies: cvxpy, pandas, numpy, matplotlib, statsmodels

Dependencies include Robust Synthetic Control (although primary specification is Ridge regression).

1. Run SC_LinReg_CJA-updatedincidents.ipynb. Change configuration cell to toggle between methods/specifications (linear regression with ridge, without ridge, RSC). nyc_ITS.R runs analysis for the ITS.
2. Generate tables: SC_LinReg_CJA_tables.ipynb reads in the outputs from each method stored in .p files in results

incidents_series_update.csv was generated by processing final_incidents_2021-05-28.csv using process_incidents.R.

Download that larger CSV, and all the raw incident files from the openICPSR data repository associated with this project.