Introduction
Students in the statistical science program learn to develop and use statistical methods to provide a probabilistic assessment of the variability in different data structures. This knowledge is applied to the quantification of the uncertainties inherent in the discoveries, summaries and conclusions that are drawn from the data analysis. The Statistical Science M.S. places emphasis on the application of statistical methods to the solution of relevant scientific, technological and engineering problems, with the goal of preparing students for professional careers
Students will obtain an M.S. in statistical science. More specifically, students will develop background on statistical theory, methods, and computing through the program coursework, with emphasis on novel methods and applications.
Undergraduate preparation for admission
We will accept students with undergraduate degrees in fields that include computer science, engineering, mathematics, natural sciences, physics, and statistics, subject to appropriate course requirements in statistics and mathematics. Undergraduate preparation in mathematics and statistics should include:
- single variable and multivariate differential and integral calculus (UC Santa Cruz equivalent AM 11A, AM 11B or MATH 19A, MATH 19B, and MATH 23A, MATH 23B);
- linear algebra (UCSC equivalent AM 10 or MATH 21);
- introductory statistics (UCSC equivalent STAT 5 or STAT 7); and
- introductory calculus-based probability and statistical inference (UCSC equivalent STAT 131 and STAT 132).
Relationship of M.S. and Ph.D. programs
The M.S. and Ph.D. programs are freestanding and independent, so that students can be admitted to either. Students completing the M.S. program may proceed into the Ph.D. program upon successful completion of the pre-qualifying examination, and application to the graduate committee and acceptance. Students in the Ph.D. program have the option of receiving the M.S. degree upon completion of the M.S. program requirements, including the capstone research project. Ph.D. core courses STAT 205B and STAT 206B can be used in place of STAT 205 and STAT 206, respectively, to fulfill the M.S. degree course requirements.
Requirements
Course Requirements
Eight core courses
M.S. students must complete eight core courses: the six 5-credit courses listed below; a 3-credit course on research and teaching (STAT 200); and a 2-credit research seminar (STAT 280B). M.S. students must complete two additional 5-credit courses from the approved list of elective courses, bringing the total non-seminar credit requirement to 43 credits. None of the additional elective courses required to satisfy the unit requirements for the M.S. program can be substituted by independent study courses (M.S. Project, Independent Study/Research, or Thesis Research).
Students in the M.S. program must take the following eight core courses:
| STAT 200 | Research and Teaching in Statistics | 3 |
| STAT 203 | Introduction to Probability Theory | 5 |
| STAT 204 | Introduction to Statistical Data Analysis | 5 |
| STAT 205 | Introduction to Classical Statistical Learning | 5 |
| STAT 206 | Applied Bayesian Statistics | 5 |
| STAT 207 | Intermediate Bayesian Statistical Modeling | 5 |
| STAT 208 | Linear Statistical Models | 5 |
| STAT 280B | Seminars in Statistics | 2 |
5-credit core courses
All core courses are 5-credit courses, except for STAT 200 and STAT 280B. STAT 200 is a 3-credit course which covers basic teaching techniques for teaching assistants, and examines research and professional training items, as well as ethical issues relating to research in science and engineering. STAT 280B is a 2-credit seminar course, which involves attending the Statistics Department colloquia and participating in the discussion session after the seminar presentation. The strict requirement for STAT 280B is for students to take it once in their first year in the program. However, students are strongly recommended to take STAT 280B each quarter throughout their graduate studies.
All core courses must be taken for a letter grade (except for STAT 200 and STAT 280B, which are given on a satisfactory/unsatisfactory basis). In order to maintain a full load for graduate standing after their first year, students take additional courses, including independent study courses, from the approved list of elective courses, appropriate to their research interests and selected in consultation with their advisors.
Electives available to MS students include:
| STAT 202 | Linear Models in SAS | 5 |
| STAT 209 | Generalized Linear Models | 5 |
| STAT 222 | Bayesian Nonparametric Methods | 5 |
| STAT 223 | Time Series Analysis | 5 |
| STAT 224 | Bayesian Survival Analysis and Clinical Design | 5 |
| STAT 225 | Multivariate Statistical Methods | 5 |
| STAT 226 | Spatial Statistics | 5 |
| STAT 227 | Statistical Learning and High Dimensional Data Analysis | 5 |
| STAT 229 | Advanced Bayesian Computation | 5 |
| STAT 243 | Stochastic Processes | 5 |
| STAT 244 | Bayesian Decision Theory | 5 |
| STAT 246 | Probability Theory with Markov Chains | 5 |
| AM 216 | Stochastic Differential Equations | 5 |
| AM 230 | Numerical Optimization | 5 |
| AM 250 | An Introduction to High Performance Computing | 5 |
| CSE 242 | Machine Learning | 5 |
| CSE 243 | Data Mining | 5 |
| CSE 249 | Large-Scale Web Analytics and Machine Learning | 5 |
| CSE 261 | Advanced Visualization | 5 |
| CSE 263 | Data Driven Discovery and Visualization | 5 |
| CSE 272 | Information Retrieval | 5 |
| CSE 277 | Random Process Models in Engineering | 5 |
| ECE 253
/CSE 208
| Introduction to Information Theory | 5 |
| ECE 256 | Statistical Signal Processing | 5 |
| ECON 211A | Advanced Econometrics I | 5 |
| ECON 211B | Advanced Econometrics II | 5 |
| ENVS 215A | Geographic Information Systems and Environmental Applications | 5 |
| ENVS 215L | Exercises in Geographic Information Systems | 2 |
ENVS 215L is the concurrent lab to ENVS 215A. The lecture/lab combination counts as one course.
Other Requirements
This is a Plan II Capstone. For the M.S. degree, students conduct an individual capstone research project in their second year (up to three quarters), and in the spring of that year participate in a seminar in which results from their project are presented. Examples of capstone research projects include: review and synthesis of the literature on a topical area of statistical science; application and comparison of different models and/or computational techniques from a particular area of study in statistics; comprehensive analysis of a data set from a particular application area.
Students must submit a proposal to the potential faculty sponsor no later than the end of the fourth academic quarter. If the proposal is accepted, the faculty member becomes the sponsor and supervises the research and writing of the project. When the project is completed and written, it must be submitted to and accepted by a committee of two individuals, consisting of the faculty advisor and one additional reader. The additional reader will be chosen appropriately from within the graduate program faculty or outside of it. Either the advisor or the additional reader must be from within the graduate program faculty.
Normative Time to Degree
The normative time to the M.S. degree (for students enrolled full-time) is two academic years.
Review of Progress
Students will be admitted to the M.S. program, not to the research group of any individual faculty member. However, each student will be matched with a first-year mentor, to ensure that adequate guidance is provided in the crucial first year of graduate school. In the second year, the role of the mentor will be played by the M.S. project advisor. Faculty advisors will be responsible for charting the progress of their students on a regular basis, and for making necessary adjustments to their plan of study and research.
The graduate program faculty will meet in the spring quarter of each academic year to review the performance of all students in the program. Based on the results from the faculty review, a written report will be provided to each student with an assessment of her/his performance and description of specific program objectives for the following academic year.
Transfer Credit
Up to three School of Engineering courses fulfilling the degree requirements of the M.S. degree may be taken before beginning the graduate program through the concurrent enrollment program. Courses from other institutions may not be applied to the M.S. degree course requirements.
Students who complete the M.S. degree in statistical science and continue onto the Ph.D. program in statistical science can transfer all applicable courses taken during the M.S. to the Ph.D. program, provided that such students meet the minimum residency requirement for Ph.D. programs at UC Santa Cruz, as specified by the UCSC Graduate Division.
Applying for Graduation
All candidates for a degree must submit an Application for Master's Degree to the Graduate Student Affairs office by the date stated in the Academic and Administrative Calendar for the quarter they wish to receive the degree. The deadline for degree applications is typically in the second week of the quarter.