Ph.D. in Statistics
The Department of Experimental Statistics is the principal source of statistical education, research, and service at LSU. This department is unique in its strong orientation toward the application of statistics. Faculty provide expert statistical support for the University community. Faculty also routinely serve on graduate committees in other departments and collaborate on interdisciplinary research projects, in addition to directing graduate students in statistics and conducting independent research programs. The department has approximately 30 graduate students who interact closely with the faculty.
The Department offers a Ph.D. degree in Experimental Statistics.
Ph.D. in Statistics
The Doctor of Philosophy in Experimental Statistics is open to students holding a BS or MS in statistics-related degree programs. To become a doctoral candidate, a student must pass a qualifying examination, meet the one-year residence requirement, and complete a minimum of 36 semester hours of approved course work beyond the Masters (specifically, 24 hours of coursework plus 12 hours of dissertation research, EXST 9000).
A major objective of the Ph.D. program in statistics will be to prepare students to meet the needs of business, industry, and academia in the statistical sciences and to provide an educated and market-ready workforce of statisticians for the economic development of Louisiana. In particular, the program will target statistics applied to the areas of industrial statistics and reliability in manufacturing and services; agricultural business including precision agriculture; biology, particularly in the areas of ecological and environmental statistics, proteomics, genomics, and bioinformatics; pharmaceuticals; and social science research.
The degree will focus on state-of-the-art, cutting-edge research in areas relevant to current developments in applied statistics with strong links to ongoing interdisciplinary research at Louisiana State University. The program will be comprehensive, and it will provide an excellent mix of statistical technical skills, computing skills relevant to statistical applications, and statistical research applied to relevant problems.
Coursework will include advanced statistical methods and advanced statistical inference, computational statistics, multivariate and generalized linear models, and modern Bayesian Methods. Opportunities for additional electives in mathematics, econometrics, geography, and engineering, among others, will be provided.
Students must satisfy all admission requirements of the Graduate School. Application materials, obtained from the department, must be completed and returned to the Graduate School. Transcripts and three letters of recommendation must also be sent to the Graduate School. Letters should be written by individuals who have knowledge of the student's academic and professional qualifications.
Admission is based on aptitude, interest, and background, as documented in application materials. Evidence of a strong aptitude comes from GRE scores and grades in previous college courses. Breadth of background, particularly in the applied sciences, is advantageous. Previous training in probability and statistics is desirable but not required.
To complete the program successfully, students need a working knowledge of multidimensional calculus and linear (matrix) algebra. Qualified students who have not had adequate training in mathematics can be admitted and allowed to schedule appropriate courses to satisfy this requirement without credit toward the degree.
Graduate assistantships, awarded competitively with the approval of the department chair, pay $30,667 for twelve months per year for a full-time assistantship of 20 hours per week. Academic qualifications and ability to carry out assistantship duties are the major considerations in awarding assistantships.
Some assistantships, particularly those funded by contracts, may require special skills or qualifications. The department normally will provide assistantship support for a maximum of two calendar years.
The Doctor of Philosophy in Experimental Statistics is open to students holding an MS in statistics-related degree programs. To become a doctoral candidate, a student must pass a qualifying examination, meet the one-year residence requirement, and complete a minimum of 36 semester hours of approved course work beyond the Masters (specifically, 24 hours of coursework plus 12 hours of dissertation research, EXST 9000).
A doctoral student in Experimental Statistics must complete the following 12-hour core:
- EXST 7104: Advanced Statistical Methods I (3 credits)
- EXST 7114: Advanced Statistical Methods II (3 credits)
- EXST 7160: Advanced Statistical Inference I (3 credits)
- EXST 7161: Advanced Statistical Inference II (3 credits)
The remaining hours of course work will be elective from 7000-level Experimental Statistics courses or graduate courses from other departments (see below) and approved by the advisory committee. A minimum of eighteen credits of course work at the 7000 level must be taken in the department. All students must complete one academic year of residence within the Ph.D. program after a program of study is filed with the Graduate School. To complete the program and obtain the Ph.D. in Statistics, students will be required to pass a general examination, to conduct original research in statistics, write a dissertation of publishable quality on this research, and to pass a final examination and defense of this dissertation. Examinations and the dissertation will follow established Graduate School guidelines.
- EXST 7047 (3hrs): Structural Equation Modeling and Hierarchical Linear Modeling
- EXST 7140 (3hrs): Survey of Modern Computational Statistics
- EXST 7137 (3hrs): Theory of Multivariate Statistics
- EXST 7139 (3hrs): Advanced Statistical Models/Analysis for Lifetime Data
- EXST 7151 (3hrs): Bayesian Data Analysis
- ECON 7630 (3hrs): Econometric Methods
- ECON 7631 (3hrs): Econometric Methods II
- ECON 7632 (3hrs): Microeconomics
- ECON 7633 (3hrs): Dynamic Econometric Theory
- MATH 7311 (3hrs): Real Analysis I
- MATH 7360 (3hrs): Probability Theory
- GEOG 7935 (3hrs): Quantitative Methods for Geographical Analysis
- EE 7660 (3hrs): Random Processes II
- CSC 7442 (3hrs): Data Mining and Knowledge Discovery