Theory & Methodology of Political Research

Graduate Methods Course at HSE Political Science Department

Modules 1,2 &3, 2016-17

Instructor:

Course Description:

In this course we cover research methods for political science in seven distinct modules: 1) Prerequisites (two sessions), including calculus, probability theory, linear algebra, and basics of working with a statistical software 2) Fundamentals of regression analysis (six sessions, two modules): including regression analysis, diagnostics of inference, regressions with time series data, nonlinear regression methods and finally causal inference using regression 3) Fundamentals of game theory and rational choice (six sessions, two modules): including pure and mixed equilibria in games of simultaneous and sequential moves, games of imperfect information, repeated games and bargaining models 4) Data collection and qualitative methods (three sessions) under two main rubrics of survey and archival methods, including structured and unstructured surveys, sampling issues and archival methods and case studies 5) Panel and Bayesian data analysis (four sessions) including hierarchical and multilevel models, fixed and random effects, survival analysis and Bayesian statistical modeling 6) Policy evaluation methods in political science (three sessions) including causal analysis methods, controlled experiments, eld experiments, and natural and quasi-experiments of history covering differences-in-differences, matching, regression discontinuity, and instrumental variable methods 7) Big Data in political science (four sessions) including four modules, social network analysis, text analysis, GIS, and machine learning & prediction.

Each of the modules of the course is followed by an assignment and a seminar dedicated to the discussion of the techniques utilized in the assignment, as well as review of practical matters, such as software usage and data processing and analysis.

Weekly lectures outline the core theory and methodology of political science, and demonstrate the usage of these methods in the political science literature. There are required readings assigned for each lecture.

Seminars are scheduled to help students to develop their practical skills via working with theoretical examples, data processing exercises, and in-class discussions with the instructor.


Part 1: PREREQUISITES


Week 1, September 5:

Course Introduction, Overview of the Course, Basic mathematics of social science

Week 2, September 12:

Research Design and Basics of Social Science Data


[ASSIGNMENT 1], Due September 19, 12 PM


Part 2: FUNDAMENTALS, REGRESSION ANALYSIS


Week 3, September 19:

Fundamentals of regression analysis, simple Ordinary Least Squares (OLS)

Week 4, September 26:

Multiple Regressions, Definition and Diagnostics of Inference

Week 5, October 3:

Multiple Regression-II

Week 6, October 10:

Regression with Time Series Data

Week 7, October 17:

Nonlinear Regression: Logit and Probit, GLM, Poisson, Negative Binomial

Week 8, October 24:

Regression & Causal Inference, Instrumental Variable Analysis (IV) & Two Stage Least Squares (2SLS)


Part 3: FUNDAMENTALS, GAME THEORY & RATIONAL CHOICE


Week 9, October 31:

Fundamentals-Nash Equilibrium in Simultaneous-Move games

Week 10, November 7:

Equilibria in Sequential Games

Week 11, November 14:

Mixed Strategy Equilibria

Week 12, November 21:

Games of Imperfect Information

Week 13, November 28:

Repeated Games

Week 14, December 5:

Strategic Decision Making in Politics, Examples


Part 4: INTERLUDE: QUALITATIVE RESEARCH DESIGN, DATA METHODS & VARIABLE PRODUCTION


Week 15, December 12:

Survey Methods I-Principles, Sampling Issues

Week 16, December 19:

Survey Methods II, Structured & Unstructured Surveys, Interviews

Week 17, December 26:

Archival and Observational Methods, Case Studies


Part 5: QUANTITATIVE METHODS, PANEL DATA, BAYESIAN INFERENCE


Week 18, January 16:

Econometrics of Panel Data Analysis- FE, RE

Week 19, January 23:

Temporal and Cross Sectional Dependency-Hierarchical Models

Week 20, January 30:

Survival Analysis, Treatment Effect in Panel Data

Week 21, February 6:

Bayesian Statistical Modeling


Part 6: POLICY EVALUATION METHODS


Week 22, February 13:

Policy Evaluation and Causal Analysis

Week 23, February 20:

Controlled Experiments (Mathematics and Methods), Field Experiments

Week 24, February 27:

Policy Evaluation & Natural and Quasi Experiments of History


Part 7: BIG DATA METHODS IN POLITICAL SCIENCE


Week 25, March 6:

Big Data Module One: Social Network Analysis

Week 26, March 13:

Big Data Module Two: Text Analysis

Week 27, March 20:

Big Data Module Three: GIS

Week 28, March 27:

Big Data Module Four: Machine Learning & Prediction