Presented as part of the ICPSR Summer Program in Quantitative Methods of Social Research, this course covers both supervised and unsupervised machine learning methods, but will place special emphasis on the (often) underappreciated suite of unsupervised learning tools. These methods are more exploratory in nature, and include cluster analysis, mixture modeling, principal and independent component analysis, manifold learning and multidimensional scaling, self-organizing maps, factor analysis and structural equation modeling, and other latent variable models.

Presented as part of the ICPSR Summer Program in Quantitative Methods of Social Research, this five-day workshop begins with an introduction to latent variable modeling (LVM), a comprehensive applied statistical methodology that includes latent class analysis (LCA) as a special case.

Presented as part of the ICPSR Summer Program in Quantitative Methods of Social Research, this workshop introduces the Bayesian multilevel model framework. Bayesian methods allow for an extremely flexible approach for estimating hierarchical models with a variety different types of dependent variables. Topics covered will be the hierarchical linear model, as well as models with limited dependent variables, summarizing results, in and out of sample predictions, and measures of model fit. No prior knowledge of Bayesian modeling is required but will be beneficial.

Presented as part of the ICPSR Summer Program in Quantitative Methods of Social Research, this workshop will cover the basics of the modern causal inference toolkit but explicitly from the standpoint of heterogeneous effects and complex structure (e.g. in panel, multilevel, and mixture populations) and the generalizability of inferences to new populations. We will focus on the development of identification strategies through the potential outcomes framework and DAGs for both simple models and models with complex structure.