Statistics Seminar: Calibration Weighting-Style Diagnostics for Nonlinear Bayesian Hierarchical Models
Presenter: Dr. Ryan Giordano, UC Berkeley Statistics
Description: Multilevel Regression with Post-stratification (MrP) has become a workhorse method for estimating population quantities using non-probability surveys, and is the primary alternative to traditional survey calibration weights, e.g.~ as computed by raking. For simple linear regression models, MrP methods admit “equivalent weights”, allowing for direct comparisons between MrP and traditional calibration weights (Gelman 2006). In the present work, we develop a more general framework for computing and interpreting “MrP local equivalent weights” (MrPlew), which admit direct comparison with calibration weights in terms of important diagnostic quantities such as covariate balance, frequentist sampling variability, and partial pooling. MrPlew is based on a local approximation, which we show in theory and practice to be accurate and meaningful for the target diagnostics. Importantly, MrPlew can be easily computed based on existing MCMC samples and conveniently wraps standard MrP software implementations.
Bio: Dr. Ryan Giordano is currently an assistant professor of statistics at UC Berkeley. Dr. Ryan Giordano earned a PhD in Statistics from UC Berkeley advised by Michael Jordan, Tamara Broderick, and Jon McAuliffe, an MSc with distinction in econometrics and mathematical economics from the London School of Economics, and undergraduate degrees in mathematics and engineering mechanics from the University of Illinois in Urbana-Champaign. Dr. Ryan Giordano has worked as a postdoctoral researcher at MIT under Tamara Broderick, as an engineer for Google and HP, and served for two years as an education volunteer in the US Peace Corps in Kazakhstan. Dr. Ryan Giordano’s research interests include machine learning, variational inference, Bayesian methods, robustness quantification, and what it even means to do statistics at all.
Hosted by: Statistics Department