Courses for the MS in Biostatistics

Meet some of your instructors

Raji Balasubramanian teaches Survival Analysis (BIOSTATS 748).

Nick Reich co-teaches R for Data Science (BIOSTATS 530 · 531 · 632).

Courses

Here is a sample of our graduate courses. You’re taught by faculty who are experts and do research in the topics they teach.

BIOSTATS 690E · Biostatistics in Action

Where your biostatistics and public health training all comes together.

In this MS capstone course, you apply everything you've learned to a real-world public health problem, working as a biostatistician. You develop your own research protocol, including a literature review, study design, and statistical analysis plan. You then carry out your analysis, write a manuscript with informative graphics, and present your findings. Taking part in every step of research design, execution and dissemination is a rewarding experience and a marketable skill. It prepares you for careers as a healthcare analyst or data scientist in health insurance, hospitals and clinic systems, health and medical device technology, county and state health departments, and pharma and life science companies.

“I have 20 years of experience in the field as an applied biostatistician/epidemiologist at a local academic medical center and look forward to guiding you on this complex and rewarding journey!”
— Alex Knee

Instructor: Alex Knee

BIOSTATS 530 · 531 · 632 · R for Data Science

R has become a preferred programming language in data science. This three-course sequence builds your skills to create powerful, robust and reusable data science tools: data wrangling, visualization and reporting (Part I); programming, modeling, iteration and web apps with R Shiny (Part II); and collaborating on code with GitHub and writing R packages (Part III).

Instructors: Nick Reich, Leontine Alkema

BIOSTATS 560 · Statistical Modeling in Health Data Science

Regression is the workhorse of health data science. You learn to identify analytic goals and to build, interpret and report linear and logistic regression models for descriptive, predictive and causal questions, using real datasets from a variety of public health settings and reproducible workflows in R.

Instructor: Alex Knee

BIOSTATS 601 · Probability and Statistical Inference for Health Data Science

Every data analysis rests on probability and statistical inference. This course builds that foundation for applied careers in biostatistics and data science: probability, maximum likelihood estimation, quantifying uncertainty, confidence intervals and hypothesis tests, and an introduction to Bayesian inference. You implement methods in R to see how and why they work.

Instructors: Jing Qian, Zhengqing Ouyang, Leontine Alkema

BIOSTATS 670 · Applied Statistical Genetics

Genomic studies produce vast, high-dimensional data. This course covers the fundamental statistical concepts and tools for analyzing genomics data from population-based association studies.

Instructor: Zhengqing Ouyang

BIOSTATS 683 · Introduction to Causal Inference

Telling causation apart from correlation is more pressing now than ever. You learn a general framework for causal inference, from stating the scientific question and defining the causal model to assessing identifiability, estimating effects and interpreting findings. Methods include G-computation, inverse weighting, and targeted maximum likelihood estimation (TMLE) with Super Learner, practiced in R labs and a final project.

Instructor: Leora Sarvet

BIOSTATS 690B · Bayesian Methods in Clinical Trials

Regulators including the U.S. FDA and EMA now encourage Bayesian approaches in clinical trials, especially for borrowing historical data and adaptive designs. This course introduces Bayesian methods for modern drug development: we discuss Bayesian inference, how to use prior information, Bayesian adaptive trial design, and advanced topics such as real-world data, dose-finding and platform trials. You read published research, implement methods in R and critically evaluate real trials.

Instructor: Leontine Alkema

BIOSTATS 730 · Applied Bayesian Statistical Modeling

Bayesian modeling is increasingly used in public health, pharma and tech, because it lets you combine data with what is already known and quantify uncertainty directly. In this course, you learn to build Bayesian models, fit them with R and Stan, interpret the results and check assumptions, from linear and logistic regression to hierarchical models. Case studies from public health and a project with a real dataset bring it all together.

Instructor: Leontine Alkema

BIOSTATS 740 · Mixed Models and Longitudinal Data

Real-world health data are often correlated: repeated measurements on the same patient, or patients treated in the same clinic. You learn to recognize correlated data, what goes wrong if you ignore it, and how to analyze and interpret it, mainly with mixed models, along with the theory behind these methods. You also strengthen your data management and programming skills in SAS and R.

Instructor: Ken Kleinman

BIOSTATS 743 · Analysis of Categorical Data in Public Health

Many health outcomes are categorical: whether someone has a disease, responds to treatment, or which stage of illness they are in. This course covers methods for categorical and discrete outcomes, from contingency tables and logistic regression to log-linear models, matched pairs, correlated data and some statistical machine learning, with both the theory and the hands-on computation and interpretation.

Instructor: Zhengqing Ouyang

BIOSTATS 748 · Survival Analysis

Many health studies follow patients until an event happens, such as recovery, relapse or death. You build a strong foundation in analyzing this time-to-event data: censoring, describing survival, comparing groups, and modeling survival with baseline and time-varying covariates, with competing risks and recurrent events as time permits. You analyze real datasets in R.

Instructor: Raji Balasubramanian

BIOSTATS 749 · Statistical Methods in Clinical Trials

Clinical trials are how new treatments are tested before they reach patients. In this course, you learn the statistical techniques for designing, analyzing and interpreting them.

Instructor: Leontine Alkema

BIOSTATS 750 · Applied Statistical Learning

Modern statistical learning methods are now widely used in medical and public health research. You learn penalized regression, classification, evaluating predictions and robust regression, along with cross-validation and the bootstrap, with a focus on the ideas behind the methods and applying them in R.

Instructor: Jing Qian