This README.txt file was generated on 07/26/2021 by
José Luis Montiel Olea, Brendan O’Flaherty, and Rajiv Sethi
i) GENERAL INFORMATION
The folders
1Scripts
2functions
3Data
4Output
contain Matlab scripts, Matlab functions, xlsx files, MAT files, and LaTeX files to generate the figures and tables reported in the paper “Empirical Bayes Counterfactuals in Poisson Regression with an Application to Police Use of Deadly Force” by José Luis Montiel Olea, Brendan O’Flaherty, and Rajiv Sethi.
ii) HARDWARE/SOFTWARE
(specifications and requirements)
All the files have been tested on both:
- A MacBook Pro @2.4 GHz Intel Core i7 (8 GB 1600 MHz DDR3) running Matlab 2021a.
iii) RECOMMENDED CITATION
When using this code please cite:
“Empirical Bayes Counterfactuals in Poisson Regression with an Application to Police Use of Deadly Force”, Montiel Olea, J.L., O’Flaherty, B., and Sethi, R., 2021.
iv) DATA & MAIN FILE OVERVIEW
- 1Scripts
This folder contains the “Master_Script.m” Matlab script, which collects different Matlab functions that are used to estimate the conditional mean function of a Poisson regression model estimated at counterfactual values of unobserved and observed covariates. The script also replicates Tables 1-7 in the paper.
NOTE: To generate Tables 8-11, include “ASSAULTS_TOTAL” (multiplying by 10, and dividing by “OFFICERS") from PD_Data_MPV_LEOKA_OKLE_CENSUS_PLUS.xlsx in section 1.
- 2functions
This folder contains the function called in “Master_Script.m” in the 1Scripts folder. These functions generate counterfactuals, and create LaTex and txt files that replicate Tables 1-7 in the paper.
- 3Data
This folder contains the xlsx file “PD_Data_MPV_LEOKA_OKLE_CENSUS_PLUS.xlsx”. The dataset contains homicide data and observed covariates for American police departments starting in 2013 and ending in 2018.
- 4Output
This folder contains MAT and LaTeX files, generated by “Master_Script.m”, included in the paper as Tables 1-7.