Big Data Analytics (PhD)

Program Overview

The University of Central Florida's Big Data Analytics PhD program trains researchers with statistics backgrounds to analyze massive datasets using advanced techniques such as predictive analytics, data mining, and statistical computing. The program combines coursework in statistics and computer science, preparing graduates for careers as data scientists and analysts in industries and research institutions. To earn the doctorate, students complete 72 credit hours of coursework, pass qualifying and candidacy examinations, and conduct original research for their dissertation.

Program Outline

The program provides a strong foundation in the major methodologies associated with Big Data Analytics, including:

• Predictive analytics
• Data mining
• Statistical analysis
The program has an interdisciplinary component that combines the strengths of statistics and computer science. It focuses on statistical computing, statistical data mining, and their application to business, social, and health problems. The program also features ongoing industrial collaborations. The Ph.D. in Big Data Analytics requires 72 hours beyond an earned Bachelor's degree.

Outline:

The program is structured as follows:

• Required Courses (42 credit hours):
• STA5104 - Advanced Computer Processing of Statistical Data (3)
• STA6106 - Statistical Computing I (3)
• STA6236 - Regression Analysis (3)
• STA6238 - Logistic Regression (3)
• STA6326 - Theoretical Statistics I (3)
• STA6327 - Theoretical Statistics II (3)
• STA6329 - Statistical Applications of Matrix Algebra (3)
• STA6704 - Data Mining Methodology II (3)
• STA7722 - Statistical Learning Theory (3)
• STA7734 - Statistical Asymptotic Theory in Big Data (3)
• STA6714 - Data Preparation (3)
• CNT5805 - Network Science (3)
• COP5711 - Parallel and Distributed Database Systems (3)
• Restricted Electives (15 credit hours):
• At least 9 credit hours must be STA coursework.
• Other courses may be included in a Plan of Study with departmental approval.
• Possible Electives:
• STA6107 - Statistical Computing II (3)
• STA6226 - Sampling Theory and Applications (3)
• STA6237 - Nonlinear Regression (3)
• STA6246 - Linear Models (3)
• STA6346 - Advanced Statistical Inference I (3)
• STA6347 - Advanced Statistical Inference II (3)
• STA6507 - Nonparametric Statistics (3)
• STA6662 - Statistical Methods for Industrial Practice (3)
• STA6705 - Data Mining Methodology III (3)
• STA6707 - Multivariate Statistical Methods (3)
• STA6709 - Spatial Statistics (3)
• STA6857 - Applied Time Series Analysis (3)
• STA7239 - Dimension Reduction in Regression (3)
• STA7719 - Survival Analysis (3)
• STA7935 - Current Topics in Big Data Analytics (3)
• CAP5610 - Machine Learning (3)
• CAP6315 - Social Media and Network Analysis (3)
• CAP6318 - Computational Analysis of Social Complexity (3)
• CAP6737 - Interactive Data Visualization (3)
• COP5537 - Network Optimization (3)
• COP6526 - Parallel and Cloud Computation (3)
• COP6616 - Multicore Programming (3)
• COT6417 - Algorithms on Strings and Sequences (3)
• COT6505 - Computational Methods/Analysis I (3)
• ECM6308 - Current Topics in Parallel Processing (3)
• EEL5825 - Machine Learning and Pattern Recognition (3)
• EEL6760 - Data Intensive Computing (3)
• FIL6146 - Screenplay Refinement (3)
• ESI6247 - Experimental Design and Taguchi Methods (3)
• ESI6358 - Decision Analysis (3)
• ESI6418 - Linear Programming and Extensions (3)
• ESI6609 - Industrial Engineering Analytics for Healthcare (3)
• ESI6891 - IEMS Research Methods (3)
• STA5825 - Stochastic Processes and Applied Probability Theory (3)
• STA7348 - Bayesian Modeling and Computation (3)
• COP6731 - Advanced Database Systems (3)
• Dissertation (15 credit hours):
• STA 7980 - Dissertation Research
• The student must select a dissertation advisor by the end of the first year.
• In consultation with the dissertation advisor, the student should form a dissertation advisory committee.
• The dissertation advisor will be the chair of the student's dissertation advisory committee.
• In consultation with the dissertation advisor and with the approval of the chair of the department, each student must secure qualified members of their dissertation committee.
• This committee will consist of at least four faculty members chosen by the candidate, three of whom must be from the department and one from outside the department or UCF.
• Graduate faculty members must form the majority of any given committee.
• A dissertation committee must be formed prior to enrollment in dissertation hours.
• The dissertation serves as the culmination of the coursework that comprises this degree.
• It must make a significant original theoretical, intellectual, practical, creative or research contribution to the student's area within the discipline.
• The dissertation can be either research‐ or project‐based depending on the area of study, committee, and with the approval of the dissertation advisor.
• The dissertation will be completed through a minimum of 15 hours of dissertation research credit.

Assessment:

• Qualifying Examination:
• A written examination administered by the doctoral exam committee at the start of the fall term (end of the summer) once a year.
• The courses required to prepare for the examination are STA 5703, STA 6704, CNT 5805, STA 6326, STA 6327 and COP 5711.
• Students must obtain permission from the Graduate Program Coordinator to take the examination.
• Students normally take this exam just before the start of their third year and are expected to have completed the exam by the start of their fourth year.
• To be eligible to take the Ph.D. qualifying examination, the student must have a minimum grade point average of 3.0 (out of 4.0) in all the coursework for the Ph.D.
• The exam may be taken twice.
• Candidacy Examination:
• Administered by the student's dissertation advisory committee and will be tailored to the student's individual program to propose either a research‐ or project‐based dissertation.
• The candidacy exam involves a dissertation proposal presented in an open forum, followed by an oral defense conducted by the student's advisory committee.
• This committee will give a Pass/No Pass grade.
• In addition to the dissertation proposal, the advisory committee may incorporate other requirements for the exam.
• The student can attempt candidacy any time after passing the qualifying examination, after the student has begun dissertation research (STA7919, if necessary), but prior to the end of the second year following the qualifying examination.
• The candidacy examination can be taken no more than two times.

Careers:

The program is specialized to prepare data scientists and data analysts who will work with very large data sets using both conventional and newly developed statistical methods.

Other:

• Students must maintain a minimum GPA of 3.0 in their POS, as well as a "B" (3.0) in all courses completed toward the degree and since admission to the program.
• PhD Students can obtain their Master's degree in Statistics & Data Science - Data Science Track along the way to their PhD degree.
• To satisfy the requirements for the MS degree, the student must complete the requirement for the MS degree.
• The student has the option of choosing between thesis option or non-thesis option.
• As will all graduate programs, independent learning is an important component of the Big Data Analytics doctoral program.
• Students will demonstrate independent learning through research seminars and projects and the dissertation.