In collaboration with the Chicago Department of Public Health, I led the development and validation of a predictive model to target home lead investigations. The source code is available on GitHub. Our work was reported in the Chicago Tribune, The Atlantic, and South Side Weekly.
Predictive Modeling for Public Health: Preventing Childhood Lead Poisoning
21st ACM SIGKDD Proceedings
E Potash, J Brew, A Loewi, S Majumdar, A Reece, J Walsh, E Rozier, E Jorgensen, R Mansour, R Ghani
Validation of a Machine Learning Model to Predict Childhood Lead Poisoning
JAMA Network Open 3 (9), e2012734-e2012734
E Potash, R Ghani, J Walsh, E Jorgensen, C Lohff, N Prachand, R Mansour
As a member of the Proactively Addressing Substandard Housing (PASH) working group, I helped draft a city ordinance proposing the Chicago Healthy Homes Inspection Program (CHHIP), a universal rental housing inspection program to protect tenants from health hazards including lead.
A Bayesian Approach to Recreational Water Quality Model Validation and Comparison in the Presence of Measurement Error
E Potash and S Steinschneider
Field Trial Design
Randomization Bias in Field Trials to Evaluate Targeting Methods
Economics Letters 167, 131-135
Prediction-Based Decisions and Fairness: A Catalogue of Choices, Assumptions, and Definitions
To Appear in Annual Review of Statistics, 2021
S Mitchell, E Potash, S Barocas, A D’Amour, K Lum