Overview
Robert E. Kass is a statistician at Carnegie Mellon University (Department of Statistics and Data Science / Machine Learning) known for foundational work on Bayesian inference, Bayes factors, and approximate Bayesian methods. He has also made major contributions to computational neuroscience.
Key Contributions / Features
- Kass-Raftery (1995) (JASA 90: 773–795): Canonical review of Bayes factors — evidence scale, Laplace and BIC approximations, and practical guidelines. One of the most-cited statistics papers.
- Kass-Steffey (1989) (JASA 84: 717–726): Approximate Bayesian inference in conditionally independent hierarchical models — the empirical Bayes framework (Laplace approximation to the marginal likelihood) that underlies the Daniels-Kass (2001) approximation.
- Daniels-Kass (1999) (JASA 94: 1254–1263): Nonconjugate Bayesian covariance matrix estimation via MCMC.
- Daniels-Kass (2001) (Biometrics 57(4): 1173–1184): Two-stage empirical Bayes shrinkage for covariance matrices — log-eigenvalue estimator, correlation shrinkage, rotation shrinkage via Givens angles.
Related