Instructor(s): Isabel Elaine Allen

Course is an introduction to the study of biostatistics. Course addresses types of data, their summarization, exploration and explanation, as well as concepts of probability and their role in explaining uncertainty. Course concludes with coverage of inference applied to means , proportions, regression coefficients and contingency tables. Throughout the course, the software program STATA will be used.

Instructor(s): Aaron W Scheffler

This is an introduction to the opportunities and challenges of using large datasets for biomedical research. Topics to be covered include: What is data science/big data? What makes it different from non-big data? What big data can and cannot do. Phases of data science: getting data, merging and cleaning data, storing and accessing data, visualizing or telling stories with data, drawing conclusions from data.

Instructor(s): Steve Shiboski

Instruction in multiple predictor analyses as a tool for control of confounding and for constructing predictive models. Topics will include exploratory data analyses, linear regression, and logistic regression. The STATA statistical package will be used.

Instructor(s): Chiung-Yu Huang

Advanced instruction in multiple predictor analyses. Topics will include survival analysis and regression for repeated measures. In the final weeks of the course, participants will receive individualized instruction for the analysis of their own data.

Instructor(s): Dave Glidden

This is a continuation of the Biostatistical Methods in Clinical Research series, covering additional methods in multi-predictor analyses and allowing more in-depth exploration of the topics cobered in Biostat I, II and III. Topics in survival analysis and longitudinal analysis will be emphasized and students are also encouraged to utilize their own projects to motivate discussion and to suggest topics of interest.

Instructor(s): Fei Jiang

The goal of this course is to equip students with core statistical concepts and methods. In this course students will learn mathematical, computational, statistical and probabilistic background; the basics of probability distributions including the definitions of density functions, cumulative distributions, moments of the distributions; theory and methods for point estimation; and methodology for the construction of hypothesis testing and confidence intervals. R statistical software will be used

Instructor(s): Jeffrey N. Martin

This course will introduce clinical researchers to the use of computer software for managing and analyzing clinical research data. Currently available statistical packages will be described and the roles of spreadsheet and relational database programs discussed. Use of STATA for managing, cleaning, describing, and analyzing data will be taught in lecture and laboratory sessions.

Instructor(s): Efstathios D Gennatas

Vast amounts of health-related data are generated daily and at an increasing rate. Our ability to extract insights from these invaluable resources depends in large part on the effective and efficient use of computational tools to preprocess, analyze and present data. This is an introductory programming course which aims to provide a solid understanding of and hands-on experience in the R language and enable further work in biostatistics, epidemiology, and machine learning/health data science.

Instructor(s): Efstathios D Gennatas, John Kornak

R programming course to enable work in any field including biostatistics, epidemiology, data science/machine learning. This course builds on students’ prerequisite core R language knowledge to cover skills in advanced data transformations, visualization, working with big (in-memory) data, report-writing, and core statistic testing.

Instructor(s): Thomas B. Newman

The course will define average causal effects in terms of potential outcomes, show when standard regression methods support causal inferences, and show how to estimate and interpret marginal causal effects. It will also cover propensity scores, for rare outcomes but common binary exposures; marginal structural models, for time-dependent treatments with time-dependent confounder/mediators; new-user designs; instrumental variables, for data with important unmeasured confounders.

Instructor(s): Jean J Feng, Mark R. Segal, John Kornak

This is a course that covers machine learning methods as they apply to areas of biomedical research and will teach how to implement the methods in R. Topics to be covered include: What is Machine learning? Prediction techniques (including classification) and methods for assessing them, Cross-validation, penalized regression methods such as lasso, boosting, bagging and ensemble methods, pattern recognition, deep learning, and data reduction methods, and machine learning meta packages in R.

Instructor(s): David A Quigley

This course provides an introduction to biostatistical methods. The course emphasizes practical considerations required to design studies, perform elementary analysis, and become an informed consumer of statistical data. Topics include study design, exploratory data analysis, the P value and hypothesis testing, power analysis, and reproducible analysis methods using the R statistical environment.