All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously.
Year: 2019
Type: article
Abstract: prediction model, U-statistics, conditional variable importance, conditional causal effects, and linear model coefficients. We then give probabilistic bounds for MCR, using a novel, generalizable technique. We apply MCR to a public data set of Broward County criminal records to study the reliance of recidivism prediction models on sex and race. In this application, MCR can be used to help inform VI for unknown, proprietary models.
Source: PubMed
Institutions: Duke University, Harvard University
Language: English
Subfield: Statistics and Probability
Field: Mathematics
Domain: Physical Sciences
Open Access status: green
Awards: Relationship Between Multiple Environmental Exposures and CVD Incidence and Survival: Vulnerability and Susceptibility, Cardiovascular Health and Air Pollution: A National Study, Casual Inference with Interference for Evaluating Air Quality Policies, Bayesian Methods for Comparative Effectiveness Research with Observational Data, Machine Learning for Health Outcomes and Quality of Care in Low-Income Populations, Environmental Health Disparities in an Older Population, Statistical Informatics for Cancer Research, Disparities in Exposure and Health Effects of Multiple Environmental Stressors Across the Life Course, Statistical Methods for Analysis of Massive Genetic and Genomic Data in Cancer Research
OpenAlex ID: W2994706149