Panel Data and Longitudinal Analysis

Instructor(s):

  • Andrew Philips, University of Colorado at Boulder

This workshop will be offered in an online video format.

Data collected over both units (e.g., survey respondents, states, countries) and time (e.g., days, months, years)—variants of which are known as time series cross-sectional, longitudinal, or panel data—are common in the social sciences. By gaining leverage across units and over time, these data help us answer important questions that would be difficult if we only looked at a single point in time (e.g., cross section) or single unit (e.g., time series): the relationship between growth and democracy, whether or not the resource curse exists, or how economic perceptions shape support for the government. Despite these advantages, panel data often show forms of heterogeneity as well as temporal and spatial dependence that make standard regression approaches inappropriate.

This course is designed to provide you with a broad understanding of the field of panel data analysis. The first week of the course will be spent familiarizing ourselves with the structure and properties of panel data. We will cover early approaches to modeling out characteristics such as unit heterogeneity and spatio-temporal dependence. In the second week, we move to various approaches to addressing heterogeneity, such as random and fixed effects. We also cover testing for and modeling dynamics. In the third week, we discuss models designed to account for heterogeneity in the effects, especially in regards to dynamic data. In the last week, we will cover approaches for small-T , large-N datasets (e.g., longitudinal surveys). Throughout, we will also discuss several smaller topics in panel data, such as pseudo-panels, missing data, and models for dichotomous dependent variables. We will use both Stata and/or R for many of these topics.

Fee and Registration: This course is part of the second four-week session. Please see our fee chart on our Registration page for the cost of attending one (or both) four-week session(s). Participants who enroll in a four-week session may take as many courses (workshops and lectures) as desired during the session for which they are enrolled. Participants in the four-week sessions are also welcome to attend all of the lectures and discussions offered in the Blalock Lecture Series.

Tags: panel data, longitudinal analysis, cross-sectional time series

Course Sections

Section 1

Location: Online -- Video format,

Date(s): July 20 - August 14

Time: 10:00 AM - 12:00 PM

Instructor(s):

  • Andrew Philips, University of Colorado at Boulder

Syllabus: