Foundations of Statistical Analysis in Political Science
3rd – 7th July, 1:00 PM – 3:30 PM
Dr. Charles Miller is a senior lecturer in politics and international relations at the School of Politics and International Relations of the Australian National University. His research interests include military organizations, the causes of war, foreign policy decision making and the philosophy of science.
Statistics can often seem daunting to the uninitiated – and political science methods are quickly becoming more complicated over time. This course attempts to simplify (and solidify) the principles of causal inference and statistical analysis so that the student can think about the fundamentals of statistical analysis for their own research project and begin to use R to apply these principles to their own data.
The course will be focused on understanding the following concepts: Understanding types of data and how to treat them; the basics of data visualization using the ggplot2 package in R; a brief introduction to thinking about causality in politics with reference to directed acyclic graphs (DAGs); bivariate statistical methods such as difference of means, crosstabulation, correlation, and simple linear regression and finally an introduction to multiple regression with reference to confounders and interactions.
This course is aimed at the graduate interested in quantitative analysis – perhaps for the first time (or for those with some limited training in other software packages such as Stata or SPSS). This course is taught on the basis that students remember no more than their high school algebra.
Upon successful completion of this course, students will have the knowledge and skills to:
- Understand and distinguish causal from correlational research in published political science research;
- Design political research using a causal framework;
- Understand the uses for different forms of data;
- Understand the basics of statistical programming using R; and
- Apply bivariate and multivariate methods to real data.
Wickham, Hadley., & Grolemund, Garrett. (2016). R for data science: import, tidy, transform, visualize, and model data. O'Reilly Media, Inc. DOI: https://r4ds.had.co.nz/
Field, Andy; Jeremy Miles, and Zoë Field. (2012). Discovering Statistics Using R. Thousand Oaks, CA: Sage.
Gelman, Andrew; and Jennifer Hill. (2007). Data Analysis using Regression and Multilevel/Hierarchical Models. Cambridge: Cambridge University Press
Recommended: Pearl, Judea and Dana Mackenzie. (2018). The Book of Why: The New Science of Cause and Effect. New York: Basic Book