The Master’s Degree in Statistics program is a tailored master’s degree in statistics for graduate students in political science. Note that, while the program is designed to serve political science graduate students, it is run by the Department of Statistics and Data Science. Students interested in this program will need to begin their additional course work during their third year of study (or before). Students are encouraged to apply for the program in their third year, but they may prefer to try the additional courses first.
Requirements for admission:
-
To be eligible for this program, students must have already passed Pol Sci 5094 Mathematical Modeling in Political Science, Pol Sci 5690 Quantitative Political Methodology, and Pol Sci 5696 Quantitative Political Methodology II and earned a grade of A- or A in these courses. Although exceptions have been made in the grade requirements at the request of political science faculty, this decision is up to the Department of Statistics and Data Science.
-
Students must obtain permission from the methodology field committee in the Department of Political Science.
- Students must formally apply to the Department of Statistics and Data Science Master of Arts program - https://sds.wustl.edu/graduate-program
Modified course requirements for the degree:
Students must meet the core course requirements for the traditional Master of Arts in Statistics (typically five courses), with two exceptions:
-
L87 SDS 5130 Linear Statistical Models may be replaced with Pol Sci 5690 Quantitative Political Methodology I and Pol Sci 5695 Quantitative Political Methodology II, with 3 additional credits produced.
- L7 SDS 5910 Practical Training in Statistics is not required.
There are three political science courses that count toward this master's degree in statistics that are required of all political science graduate students:
- Pol Sci 5103 Theories of Individual and Collective Choice II
- Pol Sci 5690 Quantitative Political Methodology I
- Pol Sci 5695 Quantitative Political Methodology II
These additional details make a total 21 credits: 15 required credits from statistics courses, plus 3 additional credits from substituting Pol Sci 5690 and Pol Sci 5695 for SDS 5130, plus 3 credits from Pol Sci 5103. Outstanding students who wish to not make the substitution can take SDS 5130 and one additional SDS elective, but only with permission. The remaining 15 credits are completed through electives and an optional thesis.
Students may choose any electives acceptable for the traditional Master of Arts in Statistics. The following additional electives are also available for students in this program:
- Pol Sci 5063 Causal Inference
- Pol Sci 5626 Applied Statistical Programming
- Pol Sci 5720 Topics in Quantitative Political Methodology: Computational Social Science
Thesis:
To be eligible for the thesis option, a student must maintain a cumulative grade point average of 3.5 or above in the first two semesters (or 18 units) of course work satisfying the program requirements. A maximum of 3 units may be used for thesis research. The thesis must be supervised by faculty with an appointment in Statistics and Data Science (e.g., a faculty member with a joint appointment in Political Science and Statistics and Data Science).
A thesis will not typically be like an “applied statistics” paper or even a standard methods paper in political science. Students should expect to write a paper that makes a contribution to knowledge in the field of statistics (or related areas like machine learning). The framing, literature review, and structure of the thesis should reflect this orientation. While some of the same underlying work can appear in your dissertation and thesis, the master’s thesis itself is unlikely to simply be a chapter of your dissertation. Students are encouraged to start the process of drafting their thesis early (at least a year in advance of the defense) and meet regularly with their supervising faculty during the drafting process to make sure the eventual draft meets the expectations of Statistics and Data Science.