Comparative Politics Applications of Latent Variable Models

Session Submission Type: Full Paper Panel

Session Description

Latent variable models play an increasingly prominent role in comparative politics research, providing data on a variety of vital but difficult-to-observe concepts. Applications range from measuring concepts as diverse as respect for human rights (Fariss 2014), democracy (Treier and Jackman 2008) and ideology (Hare et al 2015); to aggregating expert opinions on topics such as bureaucratic agency preferences (Clinton and Lewis 2008), party positions (Struthers et al 2019) and regime traits (Pemstein et al 2019). In this panel, scholars present cutting-edge research that extends the boundaries of latent variable research in comparative politics, while also providing an opportunity to discuss common concerns in this line of work.

Sub Unit

• Division 8: Political Methodology

Individual Presentations

• InCorporation: Assessing Corpus Selection for Social Science Applications - Sirus Bouchat, Northwestern University

• Which Way to Peace? Estimating Directionality in Conflict Event Data - Cassy Dorff, Vanderbilt University; Shahryar Minhas, Michigan State University

• Identity as a Latent Variable - Kyle L. Marquardt, University of Bergen

• A Mixture Model for Scaling Preferences Under Response-Style Heterogeneity - Juraj Medzihorsky, London School of Economics & Political Science

Chair

• Christopher J. Fariss University of Michigan

Discussant

• Daniel Pemstein North Dakota State University