Fundamentals of Time Series Cross Section Analyses

Lorena Barberia, University of São Paulo and Guy Whitten, Texas A & M University

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 dicult if we only looked at a single year (e.g., cross section) or single country (e.g., 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 week, building on Module I's introduction to time series, we move to modeling cross sectional time series data. 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. We discuss the fundamentals behind pooling your data, such as accounting for heterogeneity and temporal dependence. We also cover a variety of ways of presenting results from cross sectional time series models.
During the first four days, the course will involve about three hours of lecture time with breaks, then lunch, and then three to four hours of hands on instruction in analysis that takes place in smaller groups using Stata. On the fifth day, students will present a speci c project that applies the concepts introduced in the course.

DATES

This course runs January 20-24, 2020. 

TEACHING FELLOW: 

COURSE OUTLINE

Topic 1: We will introduce the basics of pooling data across time and space. This involves the notation behind cross-sectional time series data, different types of data structures, and ways to visualize and examine these data (including panel unit root tests).

Topic 2: We will begin to cover how to think about and model unit heterogeneity. We will delve into models of pooled time series data used by applied researchers. These include models with random effects, fixed effects, and panel corrected standard errors.

Topic 3: We will discuss di erent strategies for moving between theories and model specifications with pooled time series data.

Topic 4: We will focus on how to present and interpret our results. This will involve discussing simulation-based approaches.

Topic 5: We will have student presentations of a research project developed over the week. Everyone will provide feedback. If needed, we will also nish up any lectures.

PREREQUISITES

A full-semester graduate-level course in multiple regression analysis and Essentials of TS for TSCS (Module 1) or the equivalent thereof.