Merlise Clyde

Overview

Merlise A. Clyde is a Bayesian statistician (Professor, Duke University) known for work on Bayesian model averaging and variable selection, mixtures of g-priors, and wavelet/nonparametric methods; author of the R package BAS.

Key Contributions / Features

• Bayesian Adaptive Sampling (Clyde-Ghosh-Littman 2011): lead author of the BAS algorithm that samples regression models without replacement for variable selection and model averaging; maintainer of the BAS R package.
• Mixtures of g-priors (Liang et al. 2008): coauthor of the hyper-g prior families for Bayesian variable selection.

Related

• Bayesian Adaptive Sampling
• Variable Selection
• Bayesian Model Averaging
• Zellner's g-Prior
• Clyde-Ghosh-Littman (2011) Bayesian Adaptive Sampling for Variable Selection and Model Averaging
• Liang et al. (2008) Mixtures of g-Priors for Bayesian Variable Selection
• Feng Liang
• James O. Berger