Harvey

Assumption-Lean SURE-Based Shrinkage for Spatial Parameters

This paper introduces a framework for shrinkage estimation of spatial parameters (e.g., neighborhood effects, hospital performance) using Stein's Unbiased Risk Estimate (SURE) to select among or average over candidate definitions of relatedness—without requiring any one spatial prior, covariance model, or adjacency rule to be correct. The method achieves near-oracle performance: SURE selection performs nearly as well as the best rule in a candidate class, and SURE-weighted averaging matches the best fixed weighted average of trained candidates. In an empirical application to Opportunity Atlas economic mobility data across 20 commuting zones, the SURE-chosen average reduces estimated MSE by approximately 27% relative to the best non-spatial empirical Bayes benchmark.

An analysis of the Type Ia SN 2024gy and a comparison of different host extinction estimation techniques

On Wednesdays, We Ask Questions: Optimizing "Active Listening" in Automated Legal Triage and Referral

Tradeoffs are Domain Dependent: Improving Accuracy and Fairness in Property Tax Assessments

Electromagnetic pion mass splitting using a Pauli-Villars-regulated photon propagator

Depth of Maximum of Air-Shower Profiles above 10^17.7 eV Measured with the Fluorescence Detector of the Pierre Auger Observatory

From Subsumption to Satisfiability: LLM-Assisted Active Learning for OWL Ontologies

Environmental dependence of the Mass-Metallicity Star Formation Relations at z=4-10 with JWST

The strange and flavor-singlet axial form factors of the nucleon from lattice QCD