Skip to content

Academics

Graduate Programs in Statistics and Data Science

Preparing the Next Generation of Data Scientists

The graduate programs in statistics and data science are designed to develop both deep expertise and broad competence across data-driven disciplines. Whether pursuing an M.S. or a Ph.D., students gain rigorous training in statistics, operations research, machine learning and computational methods, while developing advanced specialization in their chosen research area. The curriculum emphasizes research excellence alongside strong communication, teaching and mentoring skills. Students engage in significant research projects and learn to effectively present and publish their findings. Graduates emerge as skilled data scientists who are prepared for rewarding and highly impactful careers in academia, industry or government.

Prerequisites

In general, it is expected that students possess a bachelor’s degree in mathematics, statistics or computer science. Other relevant backgrounds may also be considered. All students entering the program are expected to have undergraduate prerequisite courses (three semesters of calculus, linear algebra, statistics, probability and a computer language). Well-prepared students will have other undergraduate foundation courses (modern algebra, advanced calculus).

Student in classroom working on iPad with computer in front of her.

M.S. Program Information

Core and Electives Requirement

The M.S. core requirements consist of the eight graduate courses listed in the program timeline and four elective courses. It is strongly recommended that students take these courses according to the schedule outlined below. Any deviation from this schedule should be approved by the associate director for graduate studies and the student’s advisor.

Research

As a means of integrating the student’s program of diverse study, a master’s disquisition (project) must be completed by the end of the second year. The student makes an oral and written presentation of the master’s degree disquisition. The project does not typically contain original research. Instead, it usually presents a review of relevant literature the student has studied or an application of previously proposed methodologies to new applications.

Graduate Program Overview Apply to the Program

Program Timeline

  • Semester One (Fall)
    • Probability: MATH 8000, 3 credits.
    • Data Analysis: MATH 8050, 3 credits.
    • Statistical Programming: MATH 8830, 3 credits.
    • Attend the first-year seminar.
    • International students should enroll in the language improvement course and work toward passing the Verification of English Skills Test.
  • Semester Two (Spring)
    • Statistical Inference: MATH 8040, 3 credits.
    • Advanced Data Analysis: MATH 8850, 3 credits.
    • Computational Methods for Statistical Learning: MATH 8860, 3 credits.
    • Students who are supported as TAs should participate in the department’s teacher training course (which runs in the spring only).
    • Choose a research advisor.
    • Work with your advisor to identify a research committee (two more faculty members) and submit a committee selection form via iROAR.
    • Ideally, students will identify their research projects and start research at the end of the second semester.
  • Semester Three (Fall)
    • Machine Learning I: MATH 8710, 3 credits.
    • Electives: 6 credits.
    • Work with your research advisor to complete a plan of study. This should be submitted via iROAR early in the third semester.
    • Students should make significant progress on their research projects by the end of the third semester.
    • This is often when those on TA support begin their teaching responsibilities.
  • Semester Four (Spring)
    • Machine Learning II: MATH 8720, 3 credits.
    • Master’s Project Course: MATH 8920, 1 credit.
    • Electives: 6 credits.
    • There are many things to complete this semester before you graduate. Be sure to check the Graduate School deadlines for graduation applications and other needs.
    • Complete your research project.
    • Write up your project.
    • Defend your project. The defense will need to be scheduled according to the oral presentation guidelines. If you have questions or have issues, contact Connie McClain, student services coordinator. Oral presentation guidelines can be found on the Graduate Studies Overview page.
    • Graduate!

Ph.D. Program Information

Overview of requirements

Students admitted to this program must complete the M.S. in statistics and data science en route, regardless of prior education. Beyond the M.S. requirements, there are four requirements in the Ph.D. program: coursework, preliminary exams, comprehensive exam and dissertation. Details of these requirements are outlined below.

Preliminary Exams

The first priority of a beginning Ph.D. student is to pass the preliminary exams.

Preliminary exams are graded pass-fail. Graduate students in this track are required to pass the preliminary exams in both statistics and applied statistics. Students are given two attempts to pass these exams. The first attempt is in August after their first year, at which point students must attempt both exams. Students who do not complete the preliminary exam requirement on their first attempt are given a second attempt in January of their second year and need only take the exam(s) they failed on the first attempt. M.S. students are allowed to take prelims, and each pass and fail counts towards their progress. Any prelims taken by a graduate student become part of their permanent prelim record.

A no-show will count as a fail if a student signed up and did not withdraw by the specific withdrawal deadline unless there are unusual circumstances such as a medical excuse or family emergency. Any exception to the no-show fail policy can only be made if a written request is submitted by the student to the associate director for graduate studies and the graduate student services coordinator and approved by the associate director for graduate studies.

Prelim Topics and Preparatory Coursework

Prelim Exam Archive: A repository of past prelim exams is available to augment your preparations.

Comprehensive Oral Examinations: Within one year of completing the preliminary examinations, a PhD student must complete a comprehensive oral examination (sometimes called the “third” or “fourth” exam). This exam comprises the second half of the university’s candidacy examination. The first half is the prelim exams. As such, students may only attempt the comprehensive exam after passing the prelims. The comprehensive exam is administered by the student’s dissertation committee. This oral examination is designed to demonstrate the student’s readiness to begin their doctoral research. Upon successfully passing the comprehensive exam, the student advances to candidacy for the PhD degree.

Dissertation: The final requirement of the PhD degree is the doctoral dissertation. PhD students are required to write a dissertation detailing their original and significant contributions to the body of research in their area of concentration and defend it.

Graduate Program Overview Apply to the Program

Coursework

Coursework must include at least 24 hours of non-research, non-professional development graduate courses at the 8000 level or above. Courses taken in order to fulfill another degree may not be counted towards the degree. Courses taken outside of the core requirement (see below) should be selected from the following MATH 8020, 8060, 8070, 8080, 8090, 9010 and 9020.

Program timeline

School of Mathematical and Statistical Sciences
Copyright © Clemson University
School of Mathematical and Statistical Sciences | O-110 Martin Hall, Clemson, SC 29634
864-656-3434 | | Give to the Department