Selected Past Talks
Upcoming Talks and Presentations
“Introduction to Markov Chain Monte Carlo” (Guest Lecture for GCB533: Statistics for Genomics and Biomedical Informatics)
December 3, 2019, University of Pennsylvania, Philadelphia, PA
In this tutorial, I will review the basics of Bayesian inference with Gibbs sampling and MetropolisHastings (MH) algorithms. Emphasis will be placed on implementing Bayesian models using the software STAN and R, plotting and summarizing the output, and checking convergence diagnostics. Specific examples we will look at are: 1) random effects ANOVA, 2) linear regression, 3) logistic regression, and 4) Poisson regression. R/STAN code for these examples will be provided.
“Fast algorithms and theory for highdimensional Bayesian varying coefficient models” (Poster)
January 710, 2020, Bayes Comp 2020, University of Florida, Gainesville, FL
We introduce the nonparametric varying coefficient spikeandslab lasso (NVCSSL) for Bayesian estimation and variable selection in highdimensional varying coefficient models. The NVCSSL simultaneously estimates the functionals of the significant timevarying covariates while thresholding out insignificant ones. Our model can be implemented using a highly efficient expectationmaximization (EM) algorithm, thus avoiding the computational intensiveness of Markov chain Monte Carlo (MCMC) in high dimensions. Finally, we prove the first theoretical results for Bayesian varying coefficient models when p>>n. Specifically, we derive posterior contraction rates under the NVCSSL model. Our method is illustrated through simulation studies and data analysis.
“A robust Bayesian Copas selection model for detecting and correcting publication bias”
March 2225, 2020, ENAR 2020 Spring Meeting, Nashville, TN
The validity of conclusions from metaanalysis is potentially threatened by publication bias. Most existing procedures for handling this issue decouple testing for the presence of publication bias from estimation of unknown parameters under publication bias. Most of these procedures also assume normality of the betweenstudy random effects. This assumption may be invalid, especially if there are outliers in the studies included in the metaanalysis. Finally, there exist few procedures to quantify the magnitude of publication bias. In this talk, we simultaneously address all of these issues. First, we introduce the robust Bayesian Copas (RBC) selection model, which unifies inference and estimation and which offers robustness to strong assumptions about the distribution of the random effects. Second, we develop two new measures to quantify the magnitude of publication bias: one based on point estimates which can also be used for nonBayesian methods, and one based on the posterior distribution. We illustrate our method through simulations and two case studies.
“Fast variable selection and estimation in highdimensional Bayesian nonparametric additive models without MCMC” (Invited session on Bayesian variable selection at the Fifth EACISBA Conference: A Satellite Meeting of the 2020 ISBA World Meeting in Celebrating James O Berger’s 70th Birthday)
June 2627, 2020, Dali, Yunnan, China
The linear regression model is widely used but the assumption of linearity is often very restrictive and easily violated in practice. Generalized additive models (GAMs) provide an avenue to remove such a restrictive assumption and model nonlinear regression surfaces. In this talk, we introduce a new Bayesian approach to estimation and variable selection in highdimensional GAMs using a new prior known as the spikeandslab group lasso (SSGL). This model can be implemented with a highly efficient blockcoordinate ascent algorithm, allowing us to bypass computationally intensive algorithms like MCMC. Uncertainty quantification for our model is also made possible by using debiasing methods rather than posterior simulation.
Selected Past Talks

“A Fast New Bayesian Approach to HighDimensional Nonparametric Regression Without MCMC” (University of Florida Statistics Student Seminar, April 2019) Slides

“HighDimensional Bayesian Multivariate Linear Regression with Shrinkage Priors” (University of Florida Statistics Student Seminar, March 2018) Slides