Research Design Methods in International Re- lations: Quantitative Methods (INTR5077) - 2022/23AY Winter Semester
Course details
• Instructor: Akos Mate, email: matea@ceu.edu
• Class: Friday, 10:50-12:30, A419 CEU Vienna Campus
• Office Hours: After the class, appointment required (use email address above) at least 24 hours before.
• Credits: 2 ECTS
• There are no prerequisites for this course
Course Description
This goal of this course is to equip MA students with a detailed and substantial quantitative training which includes working from the introductory statistics to multivariate linear regression. This course is also a gentle but extensive intro- duction to the R statistical programming language. The focus is on applying statistical knowledge on real-life practical datasets, carrying out data analysis and interpreting results.
This course assumes no prior experience with statistics or with working with R, everyone with an interest in quantitative methods and data analysis is warmly invited to join, regardless of their current skill. However, learning both sta- tistical concepts and R means that this course will move quickly and requires students to continously engage with the materials. This includes short assign- ments and readings.
This course is comparable to other basic quantitative methods course in the social sciences, with an emphases on social science examples rather than the natural sciences. Those who already have basic training in quantitative methods may wish to request permission to take a more advanced quantitative methods course in another department at CEU, or to participate in another methods training course.
Bring your laptops to class and install R and RStudio using the install guide uploaded to Moodle.
Learning Outcomes
After successfully completing the course, students should be able to:
• Use R for data analysis and data cleaning
• Compute and report summary statistics
• Visualize data to communicate statistical insights
• Understand probability distributions and inference
• Compute and interpret statistical tests (Chi-Squared and t-test)
• Understand Analysis of Variance
• Understand correlation coefficients
• Run and interpret multivariate linear regressions
Assessment
1. Attendance and active participation (10%)
To be able to follow the course and profit from it attendance is essential. If you will be unable to attend a seminar, please inform the instructor in advance via email. More than two unexcused absences results in a reduction of the participation grade and more than three unexcused absences results in failure of the course.
2. Assignments (40%)
There will be 4 assignments during the semester (each worth 10%) focused on practicing skills learned in class.
3. Final paper presentation (10%)
Presenting the outline of the final paper. At this point you should have a dataset that you want to use and some research questions / hypotheses to test. The presentation should highlight the methods used (covered during the course) to carry out the research. No need to have a lengthy intro or literature review, the focus is on the research question, the data, the appropriate methods and expected results.
As part of this assignment you will also provide peer-review for another presen- tation. Highlight the positives and provide constructive suggestions.
4. Final paper (40%)
The final paper should investigate an interesting question using techniques cov- ered during the course. You need to find a topic and data by 17 February and send me an email with a very brief description. The lenght of the paper should be a minimum of 4000 words and no more than 6000 words, bibliog- raphy and footnotes included. The paper should identify an interesting puzzle, formulate a hypothesis, carry out the appropriate statistical analysis and then interpret the results. A rough guideline to the paper’s proportions would look like this:
• Intro & very focused literature on the topic (10%)
• Data and methods (25%)
• Analysis and results (30%)
• Discussion of the results (25%)
• Conclusion (10%)
Course policies
All assignments (including the final paper) are independent work (unless stated otherwise). You can discuss the assignments with your fellow students on general approaches however you are expected to work independently and be able to explain your work in your own words. Failing to follow these rules will mean a failing grade on the assignment.
All written assignments should be submitted on the CEU E-learning website on time and in the format specified. Late submission of written assignments will result in downgrading. If students submit their assignments one or two days late, their assignments will be downgraded by one third of a letter grade, for example from a B+ to a B; if the assignment is submitted on the third or fourth day it will be downgraded by two thirds of a letter grade, for example from a B+ to a B-, etc. Students are required to safely save a personal copy of all the files submitted to Moodle or sent via email and may be asked by the instructors to resubmit or reproduce parts of the assignment after the initial submission.
Failure to comply may result in a zero grade for that assignment.
Academic honesty and integrity is taken very seriously. The information on what will be considered as plagiarism and how it will be handled can be found in CEU’s Policy on Plagiarism: https://documents.ceu.edu/documents/p-1405-1.
All submitted assignments are processed through the Turnitin software, which checks the originality of students’ work.
Course readings
• For statistical concepts: OpenIntro Statistics, 4th Edition by David M. Dietz, Mine Cetinkaya-Rundel and Christopher D. Barr, pub- lished in 2022. It is available online for free as a pdf:
https://www.openintro.org/stat/textbook.php?stat_book=os
• For R and RStudio: R for data science: import, tidy, transform, visual- ize, and model data. 2017, O’Reilly Media. We will use the freely available online edition at: https://r4ds.had.co.nz/
• For data visualization: Healy, Kieran. Data visualization: a practical introduction. Princeton University Press, 2018. Free online version:
https://socviz.co/
In the course summaries below the ‘OpenIntro’ book is referred asOIS, the ‘R for data science’ is referred asR4DS.
Schedule
This is a tentative schedule which is subject to change as we will see how we can progress through the semester.
Session 1 (13 January) - R and RStudio intro
Please make sure that you have R and RStudio installed on your laptop. Use the installation guide uploaded to Moodle, which contains all the neccesary information.
Readings:
• R4DS Ch. 1., Ch. 8
Session 2 (20 January) - Working with data and visualization in R
Readings:
• R4DS Ch 11.1, 11.2, Ch 12.1, 12.2, Ch 5.1, 5.2, 5.4, 5.5
• Healy 3.1-.3.3
Session 3 (27 January)- Principles of data visualization
Readings:
• Wilke, Claus O. Fundamentals of data visualization: a primer on making informative and compelling figures. O’Reilly Media, 2019. Ch.29 (avail- able online: https://clauswilke.com/dataviz/telling-a-story.html)
Session 4 (3 February) - Summarizing data
Readings:
• OIS 2.1, 2.2 First assignment is due
Session 5 (10 February) - Probability distributions and random vari- ables
Readings:
• OIS 3.1, 3.2 (up until 3.2.5), 3.3, 4.1
Session 6 (17 February) - Foundations for inference
Readings:
• OIS 5.1, 5.2, 5.3 Second assignment is due
Session 7 (24 February) - Inference for categorical data
Readings:
• OIS 6.1, 6.2, 6.3
Session 8 (3 March) - Inference for numerical data
Readings:
• OIS 7.1, 7.2, 7.3, 7.5 Third assignment is due
Session 9 (10 March) - Intro to linear regression
Readings:
• OIS 8.1, 8.2, 8.3, 8.4
Session 10 (17 March) - Final Paper Proposal Presentation
Present your final paper proposal, with a heavy emphasis on data and meth- ods. You should have the data available by this point to give us a sneak-peek.
Each presentation will receive feed-back from two reviewer, who will provide constructive and substantive feedback on the proposed final paper.
Session 11 (24 March) - Multiple regression Readings:
• OIS 9.1, 9.2, 9.3
Fourth assignment is due
Session 12 (31 March) - Logistic regression and writing papers with R
Readings:
• OIS 9.5
• R4DS 27
