9th Annual IPSA-USP Summer School in Concepts, Methods and Techniques in Political Science and International Relations
January 8-26, 2018
The 9th Annual IPSA-USP Summer School in Concepts, Methods and Techniques in Political Science and International Relations was held at the University of São Paulo, Brazil from January 8 to 26, 2018. Jointly organized by the University of São Paulo’s Department of Political Science and Institute of International Relations and the International Political Science Association (IPSA), the Summer School is recognized as a leading program providing basic and advanced training in a range of methodologies and techniques. In 2018, the School was awarded a prestigious grant by FAPESP as a São Paulo School of Advanced Science (ESPCA). Some 162 participants from 23 countries attended, with women accounting for 49% of enrollment. A total of 312 student-modules were completed in 19 one-week courses.
Students also participated in the following four information sessions: research funding opportunities in Brazil; publishing academic research for maximum impact on shaping public policy; achieving success in graduate school; and SAGE Research Methods – Online Resources. As part of site visits, students also had a chance to learn about the work carried out at the Center for Metropolitan Studies (CEM) and the Center for the Study of Violence at the University of São Paulo (NEV-USP). On Saturday, January 20, a special workshop was held on “Coalitions in Presidential Regimes and Clarity of Responsibility in Latin America.” The workshop was organized by Lorena G. Barberia and Guy D. Whitten, and taking part were several researchers at the IPSA-USP Summer School. They presented their research on country-specific case studies in Latin America.
Three late-afternoon seminars were also held. During the first week, a seminar was held to discuss social science and methods. Allyson Benton (CIDE) and Andrew Q. Philips (University of Colorado Boulder) presented their paper entitled “Do Trump’s Policy Tweets Matter to Mexican Financial Markets?” Rafael Martins de Souza (FGV-CERI), Luís Felipe Guedes da Graça (Universidade Federal de Santa Catarina) and Ralph dos Santos Silva (Universidade Federal do Rio de Janeiro) presented their recently published article on “Politics on the Web: Using Twitter to Estimate the Ideological Positions of Brazilian Representatives.” Jonathan Phillips, currently a visiting researcher at CEPESP, Fundação Getulio Vargas and the Department of Political Science, University of São Paulo, served as the discussant. In the second week, Guy D. Whitten presented a seminar entitled “The Dynamic Pie Project: Theory↔Methods with Dynamic Compositional Data.” In the third week, a panel discussion on gender and methods was with the participation of Derek Beach (University of Aarhus), Allyson Benton (CIDE), Melani Cammett (Harvard University), and Jason Seawright (Northwestern University).
At the Summer School poster session held Thursday, January 20, 2018, participants presented 65 posters. The winners of the 2018 Poster Competition were Hannah Paul (Department of Political Science, University of Colorado Boulder); Lucas Mingardi (Department of Political Science, USP) for Comparative Politics (tie); Pedro de Castro, (Department of Political Science, USP) for Political Theory; and Eliana Alvarez, Rosario Queirolo, and Lorena Repetto (Department of Political Science, Universidad Católica del Uruguay) for Research Design.
Institutional Partners
The 2018 IPSA-USP Summer School was made possible with generous financial support from the Department of Political Science, the Institute of International Relations, and the Provost’s Office for Research at the University of São Paulo. We are grateful for the valuable support provided by FAPESP and CNPq. The Summer School was also supported by the Center for Metropolitan Studies (CEM) and the Center for Comparative and International Studies (NECI) at the University of São Paulo. Stata and Nvivo provided software licensing for the computer laboratories.
The following one-week modules were offered:
*Module 1 (January 8-12) (35 hours) *
- Basics of Quantitative Methods for Public Policy Analysis, Bruno Cautres (Sciences Po)
- Designing Feasible Research Projects in Political Science, Allyson Benton (CIDE)
- Essentials of Applied Data Analysis, Leonardo Barone (University of São Paulo)
- Essentials of Multiple Regression Analysis, Glauco Peres da Silva (University of São Paulo)
- Modeling Dynamics, Lorena Barberia (University of São Paulo), Andy Phillips (University of Colorado at Boulder)
*Module 2 (January 15 -19) (35 hours) *
- Advanced Issues in Quantitative Methods for Public Policy Analysis, Bruno Cautres (Sciences Po)
- Advances in Modeling Dynamics, Guy D. Whitten (Texas A&M University), Lorena Barberia (University of São Paulo), Andy Phillips (University of Colorado at Boulder)
- Basics of Causal Case Study Methods, Derek Beach (University of Aarhus)
- Basics of Multi-Method Research: Integrating Case Studies and Regression, Jason Seawright (Northwestern University)
- Basics of Spatial Interdependence in Theory and Practice, Laron Williams (University of Missouri)
- Building Parametric Statistical Models, Glauco Peres da Silva (University of São Paulo)
- Survey Research Design, Soledad Artiz Prillaman (Nuffield College at Oxford University)
*Module 3 (January 22 -26) (35 hours) *
- Advanced Issues in Multi-Method Research: Integrating Case Studies and Contemporary Methods for Causal Inference, Jason Seawright (Northwestern University)
- An Introduction to Relational Social Science, Patrick Thaddeus Jackson (American University)
- Conducting Field Research in Political Science: Interviewing and Mixed Methods Approaches, Melani Cammett (Harvard University)
- Mathematics for Social Scientists, Glauco Peres da Silva (University of Sao Paulo)
- Methods and Problems in Political Philosophy, Herlinde Pauer-Studer (University of Vienna)
- Modeling Dynamics in Space and Time, Guy D. Whitten (Texas A&M University) and Lorena Barberia (University of São Paulo)
- Process Tracing Case Studies, Derek Beach (University of Aarhus)
- Survey Research Analysis, Soledad Artiz Prillaman (Nuffield College at Oxford University
IPSA-USP 2018 Summer School Course Descriptions
Basics in Quantitative Methods for Public Policy Analysis
Bruno Cautrès, Sciences Po
OUTLINE
Whether they should or they shouldn’t, numbers, data and quantitative methods matter in policy and in policy analysis. Policy and political analysts use numbers treated with quantitative methods in evidence-based research about whether policy interventions are successful. Policymakers use numbers to support (sometimes normative) arguments about whether government should (or should not) provide particular services or engage in policy change and reforms. This course is the first course in a twocourse (Module 2 and Module 3) sequence designed to teach you the quantitative methods that you need for a career in public policy and also to be able to read publications using these methods.
DATES
This course runs January 8-12, 2018.
TEACHING FELLOW: Kelly Senters, University of Illinois at Urbana-Champaign
DETAILED DESCRIPTION
This first module introduces participants to major basic concepts and tools for quantitative evaluation of public policies. Among the many concepts used by specialists of causal reasoning and policy evaluation, the following will be clarified : counterfactual, potential outcomes, quasi-experiment, treatment effect, before-after effect. The course will then show how statistical methods can be useful to face these problems and to create a formal framework for quasi-experimental reasoning. The basics of regression models will be presented in relationship to testing the effect of « treatment » (like a policy change or like to be exposed to political reforms). On this aspect, the course will cover regression group comparisons (treated versus control groups) through different techniques (dummies, interactions, Chow test). At the end of the course, participants will have a clear view on the relationship between comparing treated versus control groups and the regression methods framework.
PREREQUISITES
Basic knowledge about descriptive statistics and introduction to statistical inference tests. As the course will use Stata as the software, a background in using this software is helpful, but not required. Lab sessions will include replication of some published papers that will permit participant to acquire practical skills for working with empirical data.
Designing Feasible Research Projects in Political Science
Allyson Lucinda Benton, CIDE
COURSE DESCRIPTION
This course introduces students to basic principles in the design of political science research. The goal is to help guide students in the design research projects that can be feasibly completed in BA, MA, or PhD theses or in an article manuscript. The course covers three basic topics. It begins with how to choose a research question or topic and how to set this topic within the relevant scholarly literature. It then covers the construction of causal arguments and the identification of these arguments’ testable expectations and implications that can be verified empirically. Included in this section is a discussion of the importance of identifying null hypotheses and alternative arguments. The course finishes by discussing empirical strategies for testing arguments, including case selection and the different types of qualitative and quantitative data available to researchers. Included in this section is a discussion of the identification of variables and their appropriate measures, and concept clarification and measurement. This course does not delve into the analysis of qualitative or quantitative empirical evidence, as this is covered in other courses in the summer program.
DATES: This course runs January 8-12, 2018.
TEACHING FELLOW: Hellen Guicheney
COURSE OUTLINE:
1. Research Questions: Identifying Research Questions; Indentifying (and Organizing) the Relevant Scholarly Literature
2. Constructing Arguments: Causality and Causal Mechanisms; Hypotheses and Testable Expectations/Implications of the Argument
3. Empirical Strategy: Concept Clarification and Measurement; The Use of Counterfactuals; Case Selection
4. Data Types: Qualitative (Interviews & Archives); Qualitative/Quantitative Observational; Quantitative Experimental (Natural Expermiments/Scientific Expermiments)
PREREQUISITES:
Students should be prepared either to develop a new or improve an existing research proposal or to discuss a current research project (usually, article length) that is underway. Each day, students should be prepared to discuss progress on their own projects in light of the particular topic of the class. In addition to course readings, students will be expected to read and discuss at least one award-winning conference paper and one award-winning PhD dissertation (a list of possible papers and theses will be given to the students). To ensure progress on their projects, students will be required to present written and oral advances each day.
Essentials of Applied Data Analysis
Leonardo S. Barone
COURSE DESCRIPTION
This course is designed for students who are interested in reviewing their training in statistics. It prepares students for courses offered in the IPSA-USP Summer School that require statistical training. It reviews basic probability; random variables and their distributions; confidence intervals and tests of hypotheses for means, variances, and proportions from one or two populations. To complement lectures, students apply the concepts taught in lectures to analyze problems using Excel and Stata.
DATES
This course runs January 8-12, 2018.
TEACHING FELLOW: Flávio Souza, Texas A&M University
COURSE OUTLINE
This course departs from the premise that the most effective way to learn statistics is by actively engaging in doing the statistical analysis. For each topic, we will have lectures that will be followed by sessions in which students will use data to answer questions that are important to political scientists. Although the goals of the class are primarily conceptual rather than narrowly mathematical, students should feel comfortable with engaging with mathematics, formulas, and data analysis.
By the end of the intensive one-week course, students should be able to apply basic concepts in probability theory to social science research questions, to make inferences about the distribution of populations based on a sample and to correctly conduct and interpret hypothesis tests. For those students who will be studying multivariate regression analysis in the Summer School, the course will provide an intuitive and basic review of linear regression in theory and practice.
PREREQUISITES
The course presumes students have some basic training in mathematics including arithmetic and algebra operations.
Essentials of Multiple Regression Analysis
Glauco Peres da Silva, University of São Paulo
COURSE DESCRIPTION
This five-day course is designed for students who are interested in reviewing their training in multiple regression analysis. It prepares students for courses offered in the IPSA-USP Summer School that require a background in multiple regression analysis. The intensive course starts with a discussion of the logic of the multivariate regression model and the central assumptions underlying the ordinary least squares approach. Particular emphasis will be given to multicollinearity, heteroskedasticity, and autocorrelation. To complement lectures, students apply the concepts taught in lectures to analyze problems using Stata.
For those of you considering enrolling in this course, watch the video below to find out more!
DATES
This course runs January 8-12,2018.
TEACHING FELLOW: Mauricio Izumi, University of São Paulo
COURSE OUTLINE
This course departs from the premise that the most effective way to learn multivariate statistics is by actively using the concepts discussed in class to solve problems. For each topic, we will have lectures that will be followed by sessions in which students will use empirical data to answer questions that are important to political scientists. For those students who will be studying multivariate regression analysis in the IPSA-USP Summer School, the course will provide an intuitive and basic review of linear regression in theory and practice. In the five-day course, our classes will be focused on the following topics:
Course Day Topics
Day 1 – An Introduction to the Multiple Regression Model
The Linear Regression Model with a Single Regressor
OLS Assumptions
Day 2 – The Linear Regression Model with Multiple Regressors
Hypothesis Tests and Confidence Intervals
Assessing Goodness of Fit
Day 3 – Multicollinearity
Day 4 – Heteroskedasticity
Day 5 – Autocorrelation
PREREQUISITES
The course presumes students have some basic training in mathematics including arithmetic and algebra operations. It also assumes that students have a background in statistics including basic probability; random variables and their distributions; confidence intervals and tests of hypotheses for means, variances, and proportions from one or two populations.
Modeling Dynamics
Lorena Barberia, University of São Paulo and Andrew Philips, University of Colarado at Boulder
COURSE DESCRIPTION
Time series variables (e.g. presidential approval, public mood liberalism, GDP, inflation, education level) are extremely common in the social sciences. However, due to certain properties, these series cannot always be handled using standard regression approaches. This course serves as an introduction to the world of time series analysis. We will explore the properties of time series (e.g. non-independence of observations, moving averages, unit-roots), and introduce strategies to test and model these data.
During the first three days, the course will involve about three hours of lecture time with breaks, then lunch, then three to four hours of hands on instruction in analysis that takes place in smaller groups using STATA. On the fourth day, students will work on a specific project assignment that applies the concepts introduced in the course. On the final day, we will have a wrap-up lecture and discuss group presentations.
DATES
This course runs January 8-12, 2018.
TEACHING FELLOW: Rodrigo Nakahara, University of São Paulo
COURSE OUTLINE
Day 1: The first day is designed to review standard regression using Ordinary Least Squares (OLS).
Day 2: On the second day, we extend our previous discussion to cover Generalized Least Squares (GLS). We will cover statistical and data issues (heteroscedasticity, multicollinearity, autocorrelation), and how to diagnose and address them.
Day 3: On the third day, we dive into time series analysis. We will cover how to write time series notation, how to analyze time series data, and begin to discuss threats to inference common in time series data, including autoregression and non-stationarity.
Day 4: The fourth day, we will build off previous days to add a model important to univariate time series, ARIMA models. We will cover how to estimate these models, test for statistical issues, and make forecasts using our models.
Day 5: The last day, we will have student presentations of your research project you have developed over the week. Everyone will provide feedback. If needed, we will also finish up any lectures.
PREREQUISITES
A full-semester graduate-level course in multiple regression analysis.
MODULE 2 – January 15 – 19 (35 hours)
Advanced Issues in Quantitative Methods for Public Policy Analysis
Bruno Cautrès, Sciences Po
COURSE DESCRIPTION
This is the second course in a two-course sequence (Module 2 and Module 3) designed to teach you the quantitative methods that you need for a career in public policy and also to be able to read publications using these methods. By this we mean the application of statistical methods to problems in political science and public policy.
DATES:
This course runs January 15-19,2018.
TEACHING FELLOW: Thiago Silva, Texas A&M University
INSTRUCTOR:
Bruno Cautrès, Sciences Po
COURSE OUTLINE
Building on the first course which covered basic concepts, notions and introduction to regression based reasonings, this second module provides a survey of more advanced empirical tools for political science and public policy research. The focus is on statistical methods for causal inference, i.e. methods designed to address research questions that concern the impact of some potential cause (an intervention, a change in institutions, economic conditions, or policies) on some outcome ( vote choice, income, election results, crime rates, etc).
We cover a variety of causal inference designs, including quasi-experiments, advanced regression, panel methods (fixed and random effects), difference-in-differences, instrumental variable estimation, regression discontinuity designs, quantile regression. We will analyze the strengths and weaknesses of these methods. Applications are drawn from various fields including political science, public policy, economics, and sociology.
We begin by discussing the strengths and limitations of multiple regression analysis and the relationship between regression and causal modeling. We then develop a sequence of extensions and alternatives, including : regression discontinuity, difference-in-differences, panel data, instrumental variables. The course will conclude with an introduction to some limited dependent variables techniques that are now common in political and policy analysis due to the categorical nature of many phenomens treated by political and policy analysis (binary and ordinal logit analysis).
We will learn both the techniques and how to apply them using data sets. Skills students will acquire in this course include: the capacity to reason causally and empirically, the ability critically to assess empirical work, knowledge of advanced quantitative tools, and experience in working with data sets.
PREREQUISITES
Background knowledge of multiple regression models, such as the Basics of Quantitative Methods for Public Policy Analysis course offered in Module 2, or the equivalent. As the course will use Stata as the software, a background in using this software is helpful, but not required. Lab sessions will include replication of some published papers that will permit participant to acquire practical skills for working with empirical data.
Advances in Modeling Dynamics
Lorena Barberia, University of São Paulo, Andrew Philips, University of Colorado at Boulder and Guy Whitten, Texas A & M
COURSE DESCRIPTION
Time series variables (e.g. presidential approval, public mood liberalism, GDP, inflation, education level) are extremely common in the social sciences. However, due to certain properties, these series cannot always be handled using standard regression approaches.
This five-day course is an applied intermediate-level course focusing on the techniques for testing theories with time series data. Each day the course will involve about three hours of lecture time with breaks, then lunch, then three to four hours of hands on instruction in analysis that takes place in smaller groups using STATA.
DATES
This course runs January 15-19, 2018.
TEACHING FELLOW Rodrigo Nakahara, University of São Paulo
COURSE OUTLINE
Day 1: On the first day, we will make the jump from the previous week—which covered univariate time series models—to discussing regression models more common in applied analysis (i.e. a dependent variable and multiple independent variables). We will discuss how autocorrelation is commonly treated in these models, lag structures, and interpreting the output from multivariate regression models.
Day 2: On the second day, we will cover an important topic, cointegration, which means that two or more non-stationary series to have a stable long-run relationship. Often, this is estimated using a model known as an error correction model. There has been a lot of recent discussions about cointegration and error correction, so we will spend some time talking about this debate.
Day 3: On the third day, we will relax assumptions that our independent variables are exogenous; in other words, what if our dependent variable affects our independent variables? We will cover two models, vector autoregressive models (VAR) and the cointegrating equivalent, vector error correction models (VECM).
Day 4: On the fourth day, we extend the strict stationary-non-stationary cut-points to talk about a more nuanced phenomena, fractional integration. We will discuss how to identify, test for, and model fractionally integrated series.
Day 5: On the last day, we will cover compositional time series data. Much of time series data is compositional (e.g. the level of public support for parties over time, budget allocations). We will discuss a number of recent approaches to model and visualize compositional time series data.
PREREQUISITES
A full-semester graduate-level course in multiple regression analysis and Modeling Dynamics (offered in the IPSA-USP 2017 Summer School) or the equivalent background in time series analysis.
Basics of Causal Case Study Methods
Derek Beach, University of Aarhus
COURSE DESCRIPTION
The aim of this course is to provide students with a good understanding of case-based methods and how they can be applied in your own research. This introductory course is designed for students in the early to mid-stages of a research project, where you have already defined your research question and are interested in learning about what case-based methods can offer. Some knowledge of basic social science methodology is helpful, although not required.
The focus will be on methods like small-n comparisons and in-depth case studies using Process-tracing. The core of the readings will be a forthcoming book on causal case studies co-authored by the instructor.
For those of you considering enrolling in this course, watch the video below to find out more!
DATES
This course runs January 15-19, 2018.
TEACHING FELLOW:
Natália Calfat
COURSE OUTLINE
The course covers the following topics:
DAY 1 – WHAT ARE CASE BASED METHODS, AND HOW DO THEY DIFFER FROM VARIANCE-BASED METHODS?
King, Gary, Robert O. Keohane & Sidney Verba (1994), Designing Social Inquiry. Scientific Inference in Qualitative Research, Princeton, New Jersey: Princeton University press, Chapter 3, pp. 75-114
Mahoney, James and Gary Goertz (2006), “A Tale of Two Cultures”, Political Analysis, vol. 14, no. 3, p. 227-249.
Beach and Pedersen (forthcoming) Causal Case Studies. Under contract at the University of Michigan Press, Chapter 1.
DAY 2 – WORKING WITH CONCEPTS AND THEORIES IN CASE-BASED RESEARCH
Goertz and Mahoney (2012) A Tale of Two Cultures. Princeton: Princeton University Press, Chapter 11, 12, 13, pp. 139-160.
Beach and Pedersen (forthcoming) Causal Case Studies. Under contract at the University of Michigan Press, Chapter 2, 3.
DAY 3 – COMPARATIVE METHOD
Beach and Pedersen (forthcoming) Causal Case Studies. Under contract at the University of Michigan Press, Chapter 7.
Risse-Kappen, Thomas (1991) ‘Public Opinion, Domestic Structure, and Foreign Policy in Liberal Democracies.’, World Politics, Vol. 43, No. 4, pp. 479-512.
DAY 4 – CASE STUDIES
Beach and Pedersen (forthcoming) Causal Case Studies. Under contract at the University of Michigan Press, Chapter 8, 9.
DAY 5 – MAKING INFERENCES IN CASE-BASED RESEARCH
Beach and Pedersen (forthcoming) Causal Case Studies. Under contract at the University of Michigan Press, Chapter 5, 6 (on causal inference and Bayesian framework)
Doyle, Arthur Connan (1894) Silver Blaze can be downloaded free at: http://www.wesjones.com/doyle1.htm
A constant theme throughout the course will be on debating the strengths and limitations of different case-based methods, illustrating the types and scopes of inferences that are possible, and how they differ from what variance-based methods enable.
The course will contain lectures and discussions in the morning sessions, followed by group exercises in the afternoons. Many of the exercises will utilize aspects of your own research projects.
PREREQUISITES
Some familiarity with the basics of research design and methods at the BA/MA level is preferable (though not strictly required). If no prior courses have been taken, please familiarize yourself with the basics using a book like ‘Research Methods in Politics’ (Burnham et al) (Palgrave).
Basics of Multi-Method Research: Integrating Case Studies and Regression
Jason Seawright, Northwestern University
COURSE DESCRIPTION
This course explores the most common family of multi-method research designs, involving combinations of regression analysis with qualitative methods. We will review the mechanics and assumptions involved in regression, as well as in common qualitative techniques including process tracing, comparative analysis, focus groups, in-depth interviews, and participant observation. We will then discuss efficient designs that use either regression or case studies to test assumptions and fill inferential gaps in a causal inference justified by the other method. Topics will include case selection, process-tracing designs for testing key regression assumptions, and designs that use regression as a step in a process-tracing argument. We will carry out practical exercises reviewing each method, and will discuss optimal designs for a variety of real-life inferential problems.
DATES
This course runs January 15-19, 2018.
INSTRUCTOR:
Jason Seawright, Northwestern University
TEACHING FELLOW: Kelly Senters, University of Illinois at Urbana-Champaign
COURSE OUTLINE
PREREQUISITES
A solid understanding of regression analysis and basic qualitative methods. Familiarity with statistical packages such as R and/or Stata.
Basics of Spatial Interdepence in Theory and Practice
Laron Williams, University of Missouri
COURSE DESCRIPTION
Spatial econometric models have grown in popularity in the social sciences over the last two decades, especially as scholars grapple with estimating models that match the spatial complexity of their theories. This five-day course is designed to provide students with an introduction to the use of spatial econometric models. It prepares students to carefully theorize about these spatial processes and more effectively test theoretical expectations about patterns of spatial interdependence.
We begin the course by exploring how prominent theories of social science (e.g., policy diffusion, party competition, civil war spillovers, etc) argue that the processes of nearby or similar units are related. In the second and third days we focus on issues of model specification that are unique to these models; this includes correctly specifying the manner in which the units (i.e., individuals, states, countries, etc) are spatially related, and whether the spatial interdependence occurs among variables, the errors, or the outcome itself. The fourth day emphasizes how to estimate a variety of spatial econometric models. In the final day, we explore graphical and tabular techniques to provide meaningful quantities of interest from these models. Students are encouraged to develop their own research questions about spatial processes and to bring their own data sets. In the afternoon sessions, students will use Stata and R to apply the concepts discussed in the lectures to their own research questions.
DATES
This course runs January 15-19, 2018.
Teaching Fellow: Ed Goldring, University of Missouri – Columbia
COURSE OUTLINE
Day 1: Spatial interdependence in theory and practice
This introductory seminar provides an overview of the uses of spatial econometric models in the social sciences, and discusses how these models get us closer to our causal models of politically interdependent outcomes.
Day 2: Identifying neighbors
The work horse of spatial econometric models is the W matrix, which specifies the manner in which all the observations are connected. This lecture explores the variety of options for specifying the weights matrices. We will discuss strategies for determining the appropriate patterns of interconnectedness, whether scholars begin with a strong theoretical foundation or the desire to maximize model fit. While most scholars focus on geographic patterns of interdependence, we discuss a range of other means of identifying how neighboring units are socially, politically and economically interdependent.
Day 3: Specification of the spatial interdependence
There are a variety of models in the broad family of spatial econometrics, and a useful categorization divides the spatially interdependent processes based on whether the spatial interdependence occurs in the observables, unobservables and/or outcomes. Most theories provide some insight that guides this decision; a range of tests can assert whether the theory is supported. This lecture introduces a series of tests that will detect different patterns of spatial interdependence. Moreover, we will explore how to connect the causal relationships in one’s theory to some basic spatial econometric models including the spatial lag, spatial error and spatial-X models.
Day 4: Estimating spatial econometric models
Even after scholars have identified spatial neighbors, detected patterns of spatial interdependence, and decided the appropriate model, they face the often daunting task of estimating the model. We explore a variety of techniques used to estimate spatial econometric models including OLS, MLE and two-stage least squares.
Day 5: Visualizing and depicting spatial interdependence
A recent trend in the social sciences centers on providing meaningful and easy-to-interpret quantities of interest from one’s model. This is particularly important in spatial econometric models because outcomes are often simultaneously determined with significant feedback, and/or are spatially dependent on factors occurring in nearby units. Due to these factors, simply providing the coefficients in a table provides little insight to readers beyond the sign and statistical significance. This lecture demonstrates how to calculate and provide visual depictions of substantive effects from a variety of spatial econometric models.
PREREQUISITES
A full-semester graduate-level course in multiple regression analysis and a background in simple mathematics and statistics (including probability distributions, random variables, and hypothesis tests). A strong familiarity with Stata and R are helpful, though not required.
Building Parametric Statistical Models
Glauco Peres da Silva, University of São Paulo
COURSE DESCRIPTION
In this week long course, we will learn how to build a statistical model that captures the essential features of the process that may have generated one’s observed data. Building such a model is the first step in any data analysis that will rely on parametric modelling (including for example, likelihood or Bayesian models). We will integrate a large number of common models (e.g., duration models, count models, dichotomous DV models, regression models, models of ordered data) into a single conceptual framework that will allow students to build their own new models if necessary to capture important features of the process that generated their data. We will also include a brief introduction to estimating the parameters of these models via maximum likelihood, so the week will be (somewhat) self-contained.
DATES
This course runs January 15-19, 2018.
TEACHING FELLOW:
Mauricio Izumi, University of São Paulo
COURSE OUTLINE
1. Overview of building a statistical model and probability distribution
2. Basics mathematical notation and functions
3. Basics of Calculus – Derivatives
4. Basics of probability distribution
5. Brief Introduction to Maximum Likelihood Estimation
Survey Research Design
Soledad Artiz Prillaman, Nuffield College at Oxford University
COURSE DESCRIPTION
Surveys are one of the most important sources of data for researchers and their design and analysis is therefore a critical component of a researcher’s tool kit. This is the first course in a series on Survey Research aimed at providing these important tools. This course is designed to provide an introduction to methods of survey design and implementation. This course includes both lecture-based instruction as well as hands-on practice in survey design. By the end of the course, students will be able to design their own survey and assess the quality of survey questions, evaluate various sampling strategies and in-field protocols, and identify potential methodological challenges to data quality. The course will cover methodological issues that arise in survey research, including sources of bias, measurement theory, and non-response. Students will also have the opportunity to pilot their own original survey to learn first-hand the challenges with question design, sampling, and data quality. This course is well suited for students planning to collect survey or public opinion data as well as students that work with existing survey data but desire tools to evaluate and address the quality of the data.
DATES
This course runs January 15-19, 2018.
TEACHING FELLOW: Marina Merlo, University of São Paulo
COURSE OUTLINE
Day 1 – Introduction to Survey Methods, Ethics, and Research Design
Day 2 – Sample Frames
Day 3 – Instrument Development
Day 4 – Methods of Data Collection
Day 5 – Survey Interviewing and Quality Control
MODULE 3 – JANUARY 22 – 26 (35 HOURS)
Advanced Issues in Multi-Method Research: Integrating Case Studies and Contemporary Methods for Causal Inference
Jason Seawright, Northwestern University
COURSE DESCRIPTION
This course extends the discussion of multi-method research designs to include contemporary tools for causal inference, involving combinations of matching methods, natural experiments, and randomized experiments with qualitative methods. We will review the mechanics and assumptions involved in each statistical tool. We will then discuss efficient designs that use case studies to test assumptions and fill inferential gaps in a causal inference justified by these methods for causal inference. For each quantitative method, we will analyze optimal case-selection strategies, discuss special process-tracing designs for testing assumptions distinctive to that method, and explore special considerations that arise in embedding that method as a step in a process-tracing argument. We will carry out practical exercises reviewing each method, and will discuss optimal designs for a variety of real-life inferential problems.
DATES
This course runs January 22-26,2018.
INSTRUCTOR:
Jason Seawright, Northwestern University
TEACHING FELLOW: Kelly Senters, University of Illinois at Urbana-Champaign
COURSE OUTLINE
PREREQUISITES
A solid understanding of regression analysis and basic qualitative methods. Students should also have familiarity with natural experiments, instrumental variables, matching and randomized experiments, as well as familiarity with statistical packages such as R and/or Stata.
Pragmatic Analytics: An Introduction to Relational Social Science
Patrick Thaddeus Jackson, American University
COURSE DESCRIPTION
The purpose of this course is to introduce you to a distinctive style of “thinking politics”:
processual rather than substantialist, relational rather than essentialist, configurational rather than
case-comparative. Relational analytics have their philosophical roots in pragmatism and parallels with
some currents in post-structuralism, and have traditionally been more in evidence in sociology
(particularly historical sociology) than in political science and international studies, but the problems
of various attempts to explain political outcomes by correlating attributes of units over time and
across space have led some scholars to the conclusion that the best solution might be a
comprehensive ontological re-visioning of the subject-matter at hand. Instead of looking for
essential properties of political actors or universally reliable indicators of future outcomes, a
relational sensibility highlights process, emergence, and the myriad ways that concrete social
interaction and transaction brings about contingent arrangements of meaningful practice. Primarily
a theoretical move, but with some methodological affinities, a relational turn points toward a way to
ground social-scientific scholarship in everyday social practices without sacrificing causal explanation
or theoretical generality.
In this whirlwind tour of relational thinking, after looking at some of the philosophical and
conceptual origins of relationalism, we will focus on three “flavors” of relationalism in the social
sciences: the network analysis of social positions, the distinctive style of discourse analysis best
characterized as the examination of “words in their speaking,” and practice theory. We conclude the
week with an examination of what it means to engage in a configurational analysis, as distinct from
the other kinds of (broadly neopositivist) causal analysis on offer in the social sciences.
That having been said, this is neither a technical “research design” nor a “proposal writing” class,
but is pitched as a somewhat broader level of theoretical abstraction; it is more ontological and
conceptual than it is technically operational. As we proceed through the course, however, you should
try not to lose sight of the fact that the point of theoretical reflection is to inform practical research.
Treat this course as an opportunity to set aside some time to think critically, creatively, and
expansively about the consequences of fundamental relationality for your own research.
Throughout the course we will make reference to exemplary work from Anthropology, Economics,
Sociology, and Political Science; students will be encouraged to draw on their own disciplines as well as these others in producing their reflections and participating in our lively discussions. Assigned
readings are drawn primarily from International Studies and from Sociology, and lectures will seek to
illuminate the contexts of these works; seminar discussions will focus on elucidating the arguments
of these texts and their implications for various modes of social-scientific research; workshop
activities will focus on encouraging students to connect the theoretical issues to questions and
concerns in their home fields and disciplines, and to their own research projects and interests.
DATES
This course runs January 22-26, 2018.
TEACHING FELLOW: Gabriela Rosa, University of São Paulo
COURSE OUTLINE
Lecture 1: From entities to processes
Seminar 1: A relational vocabulary
Lecture 2: Positions: social networks
Seminar 2: Ties instead of attributes
Lecture 3: Transactions: relational discourse analysis
Seminar 3: “Words in their speaking”
Lecture 4: Practices: competent performances
Seminar 4: Rules and rule-following
Lecture 5: Configurations
Seminar 5: Explanation without generalization
Conducting Field Research in Political Science: Interviewing and Mixed Methods Approaches
Melani Cammett, Harvard University
COURSE DESCRIPTION
This course focuses on the process of conducting field research from start to finish, with an emphasis on designing and carrying out mixed methods research that includes interviewing. The goal is to help guide researchers in preparing for and carrying out diverse forms of data collection in the field and to identify approaches to managing and analyzing data once collected. The bulk of the course centers on the design and execution of interview-based research and situates it within broader research projects. Key topics covered include strategies for preparing for and carrying out productive field research, which explicitly links research design to data collection in the field; varieties of interviews; the construction of different kinds of interview protocols; varied sampling strategies for interviewing; strategies for designing and conducting interviews on sensitive topics; organizing and analyzing interview-based data and aligning it with other forms of data collection; ethical considerations; and an overall assessment of the pros and cons of multi-methods research involving interviews.
DATES
This course runs January 22-26, 2018.
TEACHING FELLOW Natalia Suzuki, University of São Paulo
COURSE OUTLINE
1. Preparing for field research: Research designs to data collection in the field; designing and adapting “to-get lists”
2. Interviewing in political science: Diverse types and roles of interviews in to research designs; elite and non-elite interviews;
3. Designing interview protocols: Varieties of interviews and how to prepare for them
4. Sampling strategies in interview-based research
5. Strategies for conducting interviews on sensitive topics: Designing questionnaires on sensitive topics; carrying out interviews on sensitive topics; matched proxy interviewing
6. Organizing and analyzing interview data: NVivo and other software options; intergrating data from interviews with other data collection approaches
7. Ethical issues
8. Back to research designs: The strengths and limits of interviews, multi-methods research
PREREQUISITES
There are no prerequisites for this course. However, some experience with field research is a plus. Participants should be prepared either to develop a new or improve an existing research proposal or to discuss a current research project that involves interview-based research and to describe the role of interviews in an actual or hypothetical multi-methods research design. Each day, participants should be prepared to assess and report progress on their own projects with respect to the particular topic of the session. To ensure progress, participants will be required to present written and oral developments of their research design each day.
Mathematics for Social Scientists
Glauco Peres da Silva, University of São Paulo
OUTLINE
This course is designed for students who seek to acquire basic training in mathematics applied to quantitative analysis in the social sciences. It is directed toward students with limited training in mathematics. This course will present basic concepts commonly used in political science research, such as mathematical notation, basic set theory, various number systems, the algebra of numbers, the notion of a function, several important classes of functions, and solutions to systems of linear equations. The course will also provide an introduction to differential and integral calculus and applied matrix algebra. To complement lectures, students will apply the concepts taught in lectures to analyze problems using the mathematical and software packages commonly used in quantitative social science research.
For those of you considering enrolling in this course, watch the video below to find out more!
DATES
This course runs January 22-26,2018.
DETAILED DESCRIPTION
This course will present fundamental mathematics principles focusing on students with limited backgrounds in mathematics. This course will adopt a hands-on approach in which morning lectures will be followed by afternoon laboratory sessions in which student will apply the concepts taught in the morning to solve problems. Classes will be divided in three steps: a) lectures; b) in-class exercises; c) applications based on social science research.
Teaching Fellow: Mauricio Izumi, University of São Paulo
OUTLINE OF THE COURSE
1. Preliminaries
2. Functions and limits
3. Derivatives and Integrals
4. Linear Algebra
5. Optimization
6. Maxima and Minima Global and Local
7. Lagrange Multiplier
Required Readings
Gill, Jeff. 2006. Essential Mathematics for Political and Social Research. 1st Edition, Cambridge University Press.
Moore, Will, and David Siegel. 2013. A Mathematics Course for Political & Social Research. 1st edition, Princeton, N.J.: Princeton University Press.
Simon, Carl, and Lawrence Blume. 1994. Mathematics for Economists. 1st edition, W. W. Norton & Co.
PREREQUISITES
A background in algebra is helpful.
Modeling Dynamics in Space and Time
Guy Whitten, Texas A & M and Lorena Barberia, University of São Paulo
COURSE DESCRIPTION
Data collected over both units (e.g. municipalities, states, countries) and time (e.g. days, months, years)—known as pooled time series—are common in social science. By gaining leverage both across units and over time, this data structure helps us answer important questions that would be difficult if we only looked at a single year (i.e. cross section) or single country (i.e. time series): the relationship between growth and democracy, whether or not the resource curse exists, and how institutions shape political and economic outcomes. However, pooled time series often show types of heterogeneity that make standard regression approaches inappropriate. In this course we will explore why we might want to use pooled time series data, what issues might arise when using data in time and space, and how we can test for violations of assumptions and account for them.
This five-day course is an applied intermediate-level course focusing on the techniques for testing theories with pooled time series data. During the first three days, the course will involve about three hours of lecture time with breaks, then lunch, then three to four hours of hands on instruction in analysis that takes place in smaller groups using STATA. On the fourth day, students will work on a specific project assignment that applies the concepts introduced in the course. On the final day, we will have a wrap-up lecture and discuss group presentations.
DATES
This course runs January 22-26,2018.
TEACHING FELLOW: Yoo Sun Jung, Texas A&M University
COURSE OUTLINE
Day 1: On the first day, we will cover matrix algebra. Matrix algebra is often necessary to understand cross-sectional time series data, since individual countries are “stacked” on one another. No previous experience with matrix algebra is necessary. We will talk about operations with matrices, OLS with matrix algebra, and GLS with matrix algebra.
Day 2: On the second day, we focus on introducing pooled time series data. We will discuss the advantages and disadvantages of pooling multiple units over time. We will also discuss simple models to test for and interpret the pooling assumption.
Day 3: On the third day we will delve into models of pooled time series data used by applied researchers. These include random and fixed effects models, and panel corrected standard errors. We will also expand some of the time series diagnostics, such as unit root testing, to the pooled time series context.
Day 4: The fourth day is a gentle introduction to spatial statistics. Recent models allow us to test for and model heterogeneity across space. We will discuss various approaches to thinking about, estimating, and interpreting spatial models.
Day 5: The last day, we will have student presentations of your research project you have developed over the week. Everyone will provide feedback. If needed, we will also finish up any lectures.
PREREQUISITES
A full-semester graduate-level course in multiple regression analysis, Modeling Dynamics (offered in the IPSA-USP 2017 Summer School) and Advances in Modeling Dynamics (offered in the IPSA-USP 2017 Summer School) or the equivalent background in time series analysis.
Process Tracing Case Study Methods
Derek Beach, University of Aarhus
COURSE DESCRIPTION
The aim of this course is to introduce process tracing case study methods, enabling participants to use them in for their own research. At the core of process tracing is the in-depth analysis of causal mechanisms (process) and how mechanisms function in real-world cases. Process tracing therefore attempts to unpack and study the arrow that links causes and outcomes together in causal models, shedding light on how things work. The course will discuss process tracing’s relative strengths and limitations, and how the method can be combined productively with other methods in multi-method designs.
The course develops the two core elements of process-tracing, focusing first on the theory-side by assessing what we are actually ‘tracing’ using process-tracing methods (causal mechanisms), and second, how we are able to make evidence-based causal inferences using within-case, ‘mechanistic’ evidence. The final session deals with how process-tracing can be combined with other case-based designs like small-n comparative methods.
DATES
This course runs January 22-26, 2018.
TEACHING FELLOW:
Natália Calfat
COURSE OUTLINE
The course is intended for participants who have some knowledge of case-based methods. Ideally, participants should be mid-stage in a research project, enabling you to draw on theories and empirics from your own research to be refined during the course.
The core of the readings will be a 2016 book on causal case studies co-authored by the instructor.
The course covers the following topics:
– Day 1 – what is process tracing actually tracing?
– Day 2 – how can we make inferences in process tracing research?
– Day 3 – evaluating evidence
– Day 4 – case selection and process tracing
– Day 5 – designing process tracing research in practice
The course will contain lectures and discussions in the morning sessions, followed by group exercises in the afternoons. Many of the exercises will utilize aspects of your own research projects.
PREREQUISITES
Each student should arrive at the summer school with a 3-5 page description of their research question and tentative research design which will be presented and discussed during the course. The Process Tracing course is for participants who have either followed the Basics of causal case studies or have working experience with using case studies and knowledge of recent developments in case-based methods.
Survey Research Analysis
Soledad Artiz Prillaman, Nuffield College at Oxford University
COURSE DESCRIPTION
Surveys and public opinion polls are important sources of data, particularly for research on political behavior and preferences. This is the second course in a series on Survey Research aimed at providing these important tools. This course focuses on the analysis of existing survey data and reporting of results. The course will cover data cleaning and coding, descriptive statistics, hypothesis testing, data reduction techniques, multivariate regression of linear, binary, and categorical data, and measurement error and other sources of bias. The course will also cover the presentation of survey data through graphics and reports. By the end of the course, students will be able to take raw survey output through the process of creating presentation quality reports and graphics. This course is valuable for any researcher working with survey or public opinion data that wants an introduction to methods of survey analysis.
DATES
This course runs January 22-26,2018.
TEACHING FELLOW: Marina Merlo, University of São Paulo
COURSE OUTLINE
Day 1 – Data Processing and Reduction
Day 2 – Multivariate models of survey data
Day 3 – Dealing with non-response
Day 4 – Measurement error and sources of bias
Day 5 – Data presentation and visualization
PREREQUISITES
A background in statistics and multiple regression is strongly suggested.
