MA in Biostatistics and Data Science

The Master of Arts program in Biostatistics and Data Science provides a learning experience focused on solid theoretical foundation and practical experience. Robust course offerings, active engagement in statistical consulting, and a capstone project create ample opportunities to develop essential analytical skills. Consulting projects ranging from the simplest statistical summaries to the most complex protocols and data collection schemes allow students to get experience of working with real data analysis projects from start to finish. This hands-on experience will enable students to synthesize the acquired knowledge and integrate various courses they have taken. In the process, students will create a portfolio which demonstrates competency in data analysis, statistical programming, consulting experience with non-statisticians, oral and written communication skills.

Ideal applicants should possess solid quantitative background. An undergraduate major in statistics, mathematics, applied mathematics, physics, computer science, or engineering would make a good candidate. Prior coursework in calculus (including Calculus II) and linear algebra is expected. Having programming experience is advantageous.

Credits Required to Graduate

31 credits

Program Credit Requirements

The curriculum consists of eight required biostatistics courses which have been identified as an essential knowledge base for all students in the program. Also required, is an Ethics and Integrity in Science course. The capstone project course can be taken throughout multiple semesters but at least 3 credit hours are required for graduation. The program allows for students to choose two or more elective courses which best reflect their personal interests. Students may pursue the degree on a full-time or part-time basis.

Required Courses

10222 Ethics and Integrity in Science. 1 credit.

This course provides the basis for understanding the ethical issues related to basic scientific and medical research, including animal and human subject research, fraud, and misconduct, and governmental, institutional, and researcher responsibilities.

04224 Biostatistical Computing. 3 credits.

Prerequisites: Statistical Models and Methods I or concurrent registration

This course will cover the details of manipulating and transforming data required for statistical analysis. Topics include reshaping the data from a per-case to a per-event within a case and vice-versa. It will also cover the techniques necessary to write functions and macros in both SAS and R for developing new/modified data analysis methods. How to use R packages and C/C++ codes in R will also be covered. The LaTeX document production system is also introduced.

04221 Biomedical Applications and Consulting. 3 credits. Prerequisites: Statistical Models and Methods I & II

This course is designed for students to gain experience in statistical consulting by working with the biostatistics faculty members on various consulting projects.

04231 Statistical Models and Methods I. 3 credits.

Prerequisite: Three semesters of calculus and one semester of linear algebra

This course will cover statistical techniques for basic statistics. Topics include one-sample/two- sample tests, analyses for count data and contingency tables, basic nonparametric methods including sign, rank-sum and signed-rank tests, simple linear regression model and inference, checking model assumptions, model diagnostics, correlation analysis, one-way analysis of variance, Kruskal-Wallis one-way ANOVA, simple logistic regression, and weighted linear regression. SAS/R will be used throughout the course.

04232 Statistical Models and Methods II. 3 credits. Prerequisite: Statistical Models and Methods I

This course will cover various regression models for independent and correlated data. Topics include multiple linear regression, model diagnostics, variable selection, influence/leverage, outliers, collinearity, transformation, GLM including logistic and Poisson regression, overdispersion, GEE, mixed models, and GLMM. SAS/R will be used throughout the course.

04233 Introduction to Statistical and Machine Learning. 3 credits. Prerequisite: Statistical Models and Methods II

This course will provide an introduction to statistical learning. Core topics include variable selection, penalized linear regression such as lasso, dimension reduction including principal component analysis, flexible regression techniques including kernel smoothing/smoothing splines/generalized additive models/regression trees, support vector machine, clustering, and random forests. Other topics that can be covered include but are not limited to ridge regression, group lasso, fused lasso, adaptive lasso, SCAD, Bayesian lasso, Bayesian group lasso, Bayesian CART, BART, neural network, feature screening, graphical models, and quantile regression.

24160 Concepts in Probability and Statistics. 3 credits. Prerequisites: Calculus I and II

The course is designed for graduate students who have a background in statistics but would benefit from a review of the basic concepts in probability and statistics. It focuses on the properties of random variables including distributions, expectations, and variability measures. Topics in inferential statistics covered in this course include estimation, hypotheses testing, methods for categorical data tabulation and analysis. It also includes an overview of statistical techniques based on simulations and resampling. Key features of Bayesian analysis will be covered as well. After completion of the course, students should be well prepared for taking more advanced courses in statistics, both theoretical and applied.

24150 Bioinformatics in Omics Analysis. 3 credits.

Prerequisites: Statistical Models and Methods I and Biostatistical Computing, or consent of instructor

The course aims to introduce modern statistical and computational methods in high- throughput omics data analysis. The first half of the course focuses on fundamental statistical and computational methods applicable in different types of high-throughput omics data.

The second half covers selected important topics in bioinformatics and aims to give students a systematic view of the omics data analysis. The goals of the course include: (1) to motivate students from quantitative fields into omics research (2) to familiarize students from biological fields with a deeper understanding of statistical methods (3) to promote inter-disciplinary collaboration atmosphere in class. Students are required to have a basic statistical training (i.e. elementary statistics courses, basic calculus, and linear algebra) and basic programming proficiency (R programming is required for homework and the final project).

24297 Capstone Project. 3 credits. Prerequisites: Statistical Models and Methods II

The course is the culmination of the MA program in Biostatistics. Students will complete a project integrating their statistical analysis, data science, and application domain knowledge. A large and complex dataset will be provided to learners, and the analysis will require the application of a variety of methods and techniques introduced in the previous courses, including exploratory data analysis through data visualization and numerical summaries, statistical inference, and modeling as well as interpretations of these results in the context of the data and the research question. The project results in a written report and presentation which will improve student’s ability to communicate effectively about statistics and data science in written and oral form using both technical and nontechnical language. In addition, the project will enable students to expand their professional portfolio of coding samples, written reports and presentations.

Elective Courses

*04214 Design and Analysis of Clinical Trials. 3 credits.

Prerequisites: Statistical Models and Methods I or concurrent registration

This course covers issues in clinical trials including the clinical trial protocol, sources of bias in clinical trials, blinding, randomization, sample size calculation; phase I, phase II, phase III and hybrid trials; interim analysis, stochastic curtailment, Bayesian designs, and administrative issues in study design.

*04285 Introduction to Bayesian Analysis. 3 credits. Prerequisites: Statistical Models and Methods I

This course introduces basic concepts and computational tools for Bayesian statistical methods. Topics covered include one and two sample inference, regression models and comparison of several populations with normal, dichotomous and count data.

*04275 Applied Survival Analysis. 3 credits. Prerequisites: Statistical Models and Methods I

The following topics will be covered in this course: Basic parameters in survival studies; Censoring and truncation, Competing risks; Univariate estimation including the Kaplan-Meier and Nelson-Aalen estimator; tests comparing two or more populations, the log rank test; Semi-parametric regression, the Cox model; Aalen’s Additive hazards regression model; regression diagnostics.

04222 Statistical Computing. 3 credits. Prerequisites: Statistical Models and Methods I & II

This course is designed for students to gain experience in statistical consulting by working with the biostatistics faculty members on various consulting projects.

19210 Health and Medical Geography. 3 credits.

Geography and physical and social environments have important implications for human health and health care. This course will explore the intersections among geography, environments, and public health, with an emphasis on geographical analysis approaches for health data, to address two key questions: (1) How can concepts from geography help us to better understand health and well-being? (2) How can geographic tools, such as Geographic Information Systems (GIS) be used to address pressing questions in health and medical research? Students will become acquainted with theories and methods from health and medical geography through readings, discussion, Geographic Information Systems (GIS) laboratory exercises, and the completion of a focused course project. Throughout the semester we will use the concepts and techniques of the discipline of geography to investigate a variety of health-related topics, and laboratory exercises will center on common health and medical geography research questions. Course projects will allow students to develop a deep understanding of the geographical nature of a health problem of their choosing and will incorporate both literature review and the analysis of geographical data.

19229 Survey Research Methods. 3 credits.

Survey Research Methods is a graduate-level, 3-credit hour course that introduces students to the broad concepts of survey design, conduct, and analysis. Students will gain a detailed and comprehensive understanding of questionnaire design, sampling, data collection, survey nonresponse, and analysis of survey data. The course will include lectures, reading assignments, class discussions, individual and group presentations, and exams.

19150 Introduction to Epidemiology. 3 credits.

The course provides: 1) an overview of epidemiologic concepts; 2) an introduction to the approaches and techniques that are used to measure and monitor health status in populations; 3) an introduction to study designs to assess disease prevention and intervention; and 4) an introduction to clinical research study designs that elucidate causative factors for disease.

20151 Introduction to Epidemiology. 3 credits.

This course is designed to provide epidemiology research methodologies to clinical practical applications. Topics include diagnostic testing, meta-analysis, qualitative research, data collection and survey design. Students will learn to apply research methodologies to large data sets or populations, while understanding the reliability, and validity of their methods.

18201 Principles of Epidemiology. 3 credits.

Examines the design and implementation of case control, cohort, and mortality studies; identifies resources, databases, and problems; and critically analyzes studies in current public health literature.

Graduates of the MA program In Biostatistics and Data Science will be prepared to work in a variety of settings including pharmaceutical industry, healthcare, biomedical sciences, academics, and general data analytics.