I was a guest speaker in the seminar series course STAT/BIOST 111 at the University of Washington, where I gave a talk on Statistical Modeling for Enhanced Microbiome Biomarker Discovery. This talk explains how to perform principled statistical inference for high-dimensional regression where samples and variables are correlated. For more details, check out our paper published in Annals of Applied Statistics.

I was a guest speaker in the Wellcome Genome Campus Advanced Course “Genetic Analysis of Mendelian and Complex Disorders”, where I gave a (virtual) talk on Statistical Methods for Analysis of Correlated Data. This talk features a computationally efficient method for estimating variance components in linear mixed models. The method is illustrated on two examples, one on genome-wide association analysis and the other on gene set analysis. For more details about the method, check out this paper.

STAT312 is an introduction to statistical learning methods for biological applications. The course will cover topics such as generative models for count data, statistical modeling, clustering, hypothesis testing, multivariate analysis, classification and regression, experimental design, and teach students how to use existing software tools in R to visualize and analyze biological data.

Course materials are available on Texas A&M University eCampus or GitHub.