PolMeth, MSU
Topic: Benchmarking racial bias using causal proxies (talk).
Outcome tests (poster).
Kai Cooper
Kai Cooper
Welcome! I am a PhD candidate in Operations, Information and Decisions at The Wharton School of the University of Pennsylvania, and an affiliate of the Centre for Causal Inference in Penn Biostatistics. I study causal methodology for understanding social inequity from observational data.
Selected Working Papers
Monitoring Racial Bias in Traffic Enforcement with Noisy Proxies of Driver Behavior
Develops the first formal causal framework for benchmarking analyses in the study of discrimination.
Outcome Tests.
Reassesses the econometric outcome test through a graphical causal lens and offers new avenues forward.
Learning From Imperfect Research Designs: Automating Causal Inference When Classic Assumptions Fail
Showcases automated partial identification tools for causal inference classic assumptions in standard applied research designs are challenged.
Recent Presentations
ACIC, Salt Lake City
Topic: Benchmarking racial bias using causal proxies (talk).
Outcome tests (poster).
Isaac Newton Institute
Topic: Benchmarking racial bias using causal proxies
Poster at the Foundations of Causal Inference Workshop in
Cambridge, UK
UW Causal Reading Group (online)
Topic: Benchmarking racial bias using causal proxies
Data Science Frontiers, NYU
Topic: autobounds lecture and workshop
Joint Statistical Meetings, Nashville
Topic: Lizzy Line effects on air quality
IC2S2
Topic: Benchmarking racial bias using causal proxies
ACIC, Detroit
Topic: Benchmarking racial bias using causal proxies (poster)
Joint Statistical Meetings, Portland
Topic: Statistical challenges in the analysis of police use of force.
Awards and Grants
Tom Ten Have Award
Best Poster, ACIC Salt Lake2026
PolMeth Best Poster
Best Poster (Methods), PolMeth MSU2026
John T. Williams Prize
Best dissertation proposal in political methodology2026
AI & Analytics Grant
$7,500 award from Wharton AI & Analytics Initiative to study bias in AI decisions2026