معرفی
Todd Kuffner is an Associate Professor in the Department of Mathematics and Statistics at Washington University in St. Louis, holding a Ph.D. in Mathematics from Imperial College London. His research bridges statistical theory, Bayesian asymptotics, and machine learning, focusing on rigorous inference after model selection.
- Education:
- Ph.D., Mathematics, Imperial College London
- M.Sc., Econometrics and Mathematical Economics, London School of Economics
- M.Sc., Economics, London School of Economics
- B.A., Economics, University of Michigan
Kuffner's work investigates the validity, accuracy, and power of statistical procedures, with a focus on reconciling Bayesian, frequentist, and neo-Fisherian paradigms. His publications address higher-order asymptotics, post-selection inference, and resampling techniques for small-sample and high-dimensional settings.
Key trends in his recent articles include:
- Bootstrap methods for high-dimensional and dependent data
- Bayesian approaches to volatility estimation in financial models
- Connections between machine learning and frequentist post-selection inference
- Formal Edgeworth and von Mises expansions for robust regression
- Empirical likelihood and model selection uncertainty
Scientific contributions:
- Organizer of the Workshop on Higher-Order Asymptotics and Post-Selection Inference (WHOA-PSI) (2016-2020)
- Editorial roles at Harvard Data Science Review, Sankhya Series A, and Journal of the American Statistical Association
- Recipient of NSF grants for collaborative research
His advising and organizational efforts emphasize collaborative research and innovative conference design, including interactive forums and workshops.
