CIQLE One-Day Workshop
Introduction to Log-Linear and Latent Class Models

Richard Breen

Professor of Sociology
Director of Graduate Studies
Co-Director, Center for Research on Inequalities and the Life Course (CIQLE)
Yale University

Breen Photo
Saturday, November 21st, 2009, 9:30 AM-5:30 PM
Yale Department of Sociology
140 Prospect Street
Room 102A.

This one day workshop provides an introduction to log-linear and log-multiplicative models for cross-classified data and to latent class models. Log-linear models have been widely used in the past 30 years, particularly applied to situations in which we are interested in the association, or sets of associations, between nominal or ordinal variables. Latent class models are a natural extension of log-linear models which have many applications across the behavioral sciences because they provide a way of approximating any distribution of unmeasured heterogeneity. They are used to address problems of measurement error, unmeasured heterogeneity in event history and other models, and related issues. They are also sometimes known as discrete mixture models.

We will look at a range of models and applications and estimate them using the free software, lEM, which can be integrated with standard packages such as R.


Preliminary reading:

Powers, Daniel and Yu Xie. 2000. Statistical Methods for Categorical Data Analysis. Academic Press. Chapter 4.

Clogg, Clifford. C. 1995. “Latent Class Models” in Arminger, Gerhard, Clifford C. Clogg and Michael E. Sobel (eds.) Handbook of Statistical Modeling for the Social and Behavioral Sciences. Chapter 6.

Breen, Richard. 2000. “Why is Support for Extreme Parties Underestimated by Surveys? A Latent Class Analysis”. British Journal of Political Science 30, 2: 375-382.

Breen, Richard. 2006. Methodological developments in analyzing cross-country social mobility. Unpublished paper.

Richard Breen joined the Yale Sociology faculty in January 2007. He was previously an Official Fellow of Nuffield College, Oxford. Currently, he is a Fellow of the British Academy, a Member of the Royal Irish Academy and a member of Academia Europaea. Richard serves as a member of the Scientific Committee of the Centro de Estudios Avanzados en Ciencias Sociales, Juan March Institute, Madrid and on the Scientific Advisory Board of the Mannheimer Zentrum für Europäische Sozialforschung.

His research interests are social stratification and inequality, and the application of formal models in the social sciences.