Harvard Chan School

BIO 233: Methods II – Generalized Linear Models and Survival Analysis (2012-2015)

BIO 233 is an intermediate-level graduate course in the analysis of continuous, categorical, and survival response data. For the most part, the focus is on regression modeling as a tool for data analysis, with estimation and inference presented from both the frequentist and Bayesian perspectives.
Course materials from 2015

BIO 245: Multivariate and Correlated Data Analysis (2016-2020)

BIO 245 is a high-level graduate course in the analysis of dependent multivariate and longitudinal data. In particular, the courses presents extensions of linear and generalized linear models to the analysis of dependent data, with emphasis on parametric and semi-parametric estimation methods. Additional topics include missing data and time-dependent covariates.
Course materials from 2019

BIO 223: Applied Survival Analysis (2021-)

BIO 223 is a graduate course in the analysis of time-to-event data. The target audience is a mix of: students pursuing a Masters degree in Biostatistics; students pursuing Masters and PhD degrees in fields other than Biostastistics; and, clinicians pursuing MPHs. The scope of the course includes: censoring and truncation; parametric likelihood-based analysis; non-parametric methods such as the Kaplan-Meier estimator of the survivor function and the log-rank test; sample size/power calculations; regression-based analyses, including those based on the accelerated failure time model, the Cox model, and pooled logistic regression; causal inference for time-to-event outcomes; and, competing and semi-competing risks analysis.
Course materials from 2021

Harvard Medical School/MIT

HST 190: Introduction to Biostatistics (2017-2019)

This course, offered to students in Harvard-MIT Health Sciences and Technology program, presents the fundamentals of biostatistics, with the aim of training students to comprehend, critique and communicate findings from the biomedical literature. Major topics covered include probability theory, hypothesis testing, theory of estimation, clinical trials linear and logistic regression, survival analysis, as well as how to perform statistical analysis using MATLAB.
Course materials from 2019

University of Washington

BIOST/STAT 572: Advanced Applied Linear Models – Prediction and Smoothing (2007)

BIOST/STAT 572 was a high-level graduate course on modern methods (at least by 2007 standards!) for prediction and smoothing.
Course materials from 2007

Short Courses

An Introduction to WinBUGS

In the summer of 2008 I taught a two-day short course on WinBUGS at the Summer School on Bayesian Modeling and Computation, at the University of British Columbia.