Essex Summer School in
Social Science Data Analysis

Daniel Stegmueller

is a Lecturer in the department of Government at the University of Essex. Previously he was Prize Research Fellow at Nuffield College, University of Oxford. He has taught a number of courses and workshops on hierarchical models, missing data models and Bayesian statistics in Essex, Mannheim, Berne, and Oxford. His research interests focus on the intersection of comparative political economy and individuals’ political behavior, modern latent variable models, multilevel models, and Bayesian statistics. His work has been published in the American Journal of Political Science, Public Opinion Quarterly, and Political Analysis

2N Modeling Heterogeneity in Cross-sectional and Panel Data

Daniel Stegmueller, University of Essex
22 July - 2 August (two week course / 35 hrs)

Detailed Course Outline [PDF]

Course Content

This course introduces a range of recently developed methods that deal with heterogeneity. Heterogeneity refers to differences between groups, such as individuals and countries, which are due to omitted or unobserved factors. Commonly employed approaches try to correct for such factors. We will take a different approach and build explicit models for heterogeneity between individuals or groups allowing us to answer questions such as: Does the effect of income on redistribution preferences differ between different subgroups of individuals? Does the effect of parties’ policy on vote choice differ between countries? Do different subgroups of a population follow different patterns of attitude or preference change? Do unemployment and poverty dynamics differ between (unobserved) subgroups? The models presented in this course will help you answers such questions. Among others, we will discuss:

(1) Heterogeneity in cross sectional data:
• Multilevel models for heterogeneity between groups (countries, organization etc.)
• Latent class or finite mixture regression models for effect heterogeneity between subgroups

(2) Heterogeneity in panel data:
• Fixed and random effects models for panel data with linear as well as categorical outcomes
• Nonparametric random effects models for panel data: relaxing the common assumption of normal distributed random effects
• Dynamic panel models: modeling state-dependence (for example the stability of preferences or attitudes) and individual heterogeneity
• • Markov models: modeling transitions processes through time (such as the dynamics of partisanship or vote choice)

Course Objectives

We will discuss a wide range of models relevant for applied research in political science, sociology, and economics. You will learn the models’ theoretical properties, but we will spend a substantial amount of time on their estimation, presentation and interpretation.

Course Prerequisites

You should be familiar with basic matrix algebra and probability theory. A basic familiarity with data management (with Stata or R) is helpful but not strictly necessary.

Example Reading

McAtee, Andrea & Wolak, Jennifer. Why People Decide to Participate in State Politics. Political Research Quarterly, 2011, 64, p. 45-58

Imai, Kosuke & Tingley, Dustin. 2012. A Statistical Method for Empirical Testing of Competing Theories. American Journal of Political Science, 56, p. 218-236.

[top of page]