Master of Science in Data Science
Academic Requirements: Students who apply to our M.S. program should have 2 semesters of calculus or 2 semesters of engineering calculus.
The Master of Science program in data science requires 30 s.h. of graduate credit. It aims to train the next generation of data scientists with the analytical and technical skills to explore, formulate and solve complex data-driven problems in science, industry, business and government. The program focuses on the theory, methodology, application and ethics for working with and learning from data. Students will acquire the abilities to develop and implement new or special purpose analysis and visualization tools, and a fundamental understanding of how to quantify uncertainty in data-driven decision-making.
The coursework includes six core courses covering the fundamentals of data science including probability and statistics; data storage, access, and management; and data visualization, exploration, modeling, analysis and uncertainty quantification. Students will acquire hands-on experience in solving real-world problems, communication skills and data ethics via a required capstone project. Students choose three electives (9 s.h.) from a wide variety of courses on specialized data science topics offered by Statistics, Biostatistics, Computer Science and Business Analytics to enhance their skill set, based on their interests and career goals.
MS students in data science must maintain a g.p.a. of at least 2.75 in all work toward the degree and in additional relevant course work.
The M.S. with a major in data science requires the following coursework.
All of these:
|DATA:4750||Probabilistic Statistical Learning||Spring||3|
|DATA:5890||M.S. Data Science Practicum||Spring and Fall||2|
|DATA:3120 / STAT:3120||Probability and Statistics||Fall||4|
|DATA:3200 / STAT:3200||Applied Linear Regression||Spring and Fall||3|
|DATA:4540 / STAT:4540||Statistical Learning||Fall||3|
|DATA:4580 / STAT:4580||Data Visualization and Data Technologies||Spring||3|
|DATA:5400 / STAT:5400||Computing in Statistics||Fall||3|
At least 9 s.h. from these:
|ACTS:6200 / DATA:6200||Predictive Analytics||Spring||3|
|BAIS:6210||Data Leadership and Management||TBD||3|
|BIOS:4150 (NEW)||Data Science Foundations in R||TBD||3|
|BIOS:6721||Machine Learning for Biomedical Data|
|CS:4310||Design and Implementation of Algorithms||TBD||3|
|CS:4470||Health Data Analytics||TBD||3|
|CS:5110||Introduction to Informatics||TBD||3|
|CS:5630||Cloud Computing Technology||TBD||3|
|DATA:3210 / STAT:3210||Experimental Design and Analysis||Fall||3|
|DATA:4880||Data Science Creative Component||Fall||2|
|MATH:4840||Mathematics of Machine Learning||TBD||3|
|STAT:4560||Statistics for Risk Modeling I||Fall||3|
|STAT:5810||Research Data Management||Fall||3|
|STAT:6530||Environmental and Spatial Statistics||Every other Fall||3|
|STAT:6550||Introductory Longitudinal Data Analysis||Fall||3|
|STAT:6560||Applied Time Series Analysis||Every other Spring||3|
3. Sample Schedule for MS Students in Data Science
Year 1 Fall Semester
STAT:3120 Probability and Statistics
STAT:3200 Applied Linear Regression
STAT:4540 Statistical/Machine Learning
STAT:5400 Statistical Computing
Year 1 Spring Semester
DATA:4750 Probabilistic Statistical Learning
STAT:4580 Data Visualization and Data Technologies
Two electives (or one, if two are taken in Year 2 Fall)
Year 2 Fall Semester
DATA:5890 MS Data Science Practicum*
One elective (or two)
* Students may substitute DATA:5890 by an appropriate internship/summer work experience, with pre-approval by the course instructor.
Probability and Statistics (STAT: 3120, 4 s.h.). Basic concepts of probability, statistical models, discrete and continuous random variables and their distributions, expectations, conditional expectations, estimation of parameters, testing statistical hypotheses.
Applied linear regression (STAT: 3200, 3 s.h.). Regression analysis with focus on applications; model formulation, checking, selection; interpretation and presentation of analysis results; simple and multiple linear regression; logistic regression; ANOVA; hands-on data analysis with computer software.
Statistical Learning (STAT: 4540, 3 s.h.). Introduction to supervised and unsupervised statistical learning, with a focus on regression, classification, and clustering; methods will be applied to real data using appropriate software; supervised learning topics include linear and nonlinear (e.g., logistic) regression, linear discriminant analysis, cross-validation, bootstrapping, model selection, and regularization methods (e.g., ridge and lasso); generalized additive and spline models, tree-based methods, random forests and boosting, and support-vector machines; unsupervised learning topics include principal components and clustering. Requirements: an introductory statistics course and a regression course. Recommendations: prior exposure to programming and/or software, such as R, SAS, and Matlab.
Data Visualization and Data Technologies (STAT: 4580, 3 s.h.). Introduces common techniques for visualizing univariate and multivariate data, data summaries, and modeling results. Students will learn how to create and interpret these visualizations, and to assess effectiveness of different visualizations based on an understanding of human perception and statistical thinking. Data technologies for obtaining and preparing data for visualization and further analysis will also be discussed. Students will also learn how to present their results in written reports and to use version control to manage their work.
Computing in Statistics (STAT: 5400, 3 s.h.). Python, R; database management; graphical techniques; importing graphics into word-processing documents (e.g., LaTeX); creating reports in LaTeX; SAS; simulation methods (Monte Carlo studies, bootstrap, etc.).
Probabilistic Statistical Learning (DATA:4750, 3 s.h.). This course focuses on essential machine learning and statistics ideas that are critical in analyzing modern complex and large data. Selected topics are covered in supervised learning: linear models, deep neural networks, and non-parametric models. Besides supervised learning, essential topics from non-linear dimension reduction, clustering, and recommender systems are part of the course.
Master’s Second-Year Core Courses (DATA:5890 MS Data Science Practicum) (1 course totaling 2 semester hours). Each student will be supervised by a faculty member to complete a project that solves a real‐world problem using knowledge gained from the core courses. Students are required to submit a written report and give an oral presentation of their projects; the written report must include the background and significance of the problem, analysis method, presentation and interpretation of the results including tables and visualization, discussion, and references, plus appendices comprising technical details and documentation of computer code used in the analysis. A capstone committee consisting of three faculty members will evaluate the capstone projects and assign the final grades (S or U), with inputs from the supervising faculty members.