This is a joint MS program offered by the departments of Computer Science (College of Engineering) and Statistics (College of Arts and Sciences). Half of the coursework for the degree consists of graduate courses in computer science while the other half consists of graduate courses in statistics. Students graduating will have the skills in computer science to handle large data sets (big data). They will be capable of writing software to work with these large data sets and they will further have the statistical skill to model and analyze sub data sets of interest. They will possess sufficient expertise in both areas to effectively communicate with statisticians and computer scientists at the professional level.
The job opportunities in this field are rapidly growing. According to the McKinsey Global institute, the demand for people with deep analytical skills in the U.S. will face a shortfall of 140,000 to 190,000 by 2018. With this demand, job prospects for graduates of our program are excellent.
Briefly, the computer science courses in the program give students technical expertise in the advanced storage, retrieval, and processing of big data and data base systems. They will have advanced training in R software to handle and analyze big data. Their work in statistics includes the analysis of complicated statistical models which are needed in the analysis of big data. They will also have graduate training in the statistical language SAS. They will be capable of writing statistical software to handle existing and/or newly developed statistical methodology. The capstone for the program is a masters project course taken over two terms. In this course the student chooses a problem (topic) in Data Science on which to work under the supervision of a CS and/or STAT faculty member(s). At the end of the first term, the student will turn in a written proposal defining the problem, proposed solution(s), and a complete literature search. In the second term, the student will obtain a solution to the problem and present a written report defining the problem and his/her solution. Examples include: an unsolved problem involving data science at a local industry; an unsolved consulting problem involving data science drawn from a research problem at WMU; or an in depth study of a computationally intensive statistical method. Best projects, written in Sweave or Latex, will be submitted for publication in Data Science journals.
Entrance requirements for the program include: Courses in linear algebra, calculus I-III, introductory course in statistical methods, probability (post calculus), introduction to R software, and a strong background in an object oriented programming language such as Java or C++.