Empirical Modeling of Social Science Theory: Advanced Topics
- Robert J. Franzese, University of Michigan
This is a course in specifying, estimating, and interpreting empirical models of the complex context-conditionality and the ubiquitous temporal dependence, as well as spatial interdependence and endogeneity, that characterizes modern, sophisticated social science theory. As our theoretical understandings have advanced, their observable implications for empirical outcomes have grown correspondingly more sophisticated. In modern social science theories, the effects of most conditions are not constant; rather, they vary depending on many features of the context in which that condition occurs. The outcomes observed in some spatial unit at some time depend, according to our theoretical and substantive understandings, on those in other units and/or other times. And, we now understand better that just about everything in social science causes and is caused by (i.e., is endogenous to) just about everything else.
The course will emphasize how to specify empirical models that reflect these complex substantive-theoretical understandings, and then how to estimate, interpret, and present the results of such empirical models. The empirical-methodological tools we will cover in this pursuit include interaction models (nonlinear interactions, nonlinear least-squares) and dynamic models (conditional dynamics, time-series and spatial regression, and systems-of-equations estimation). The models work for continuous and for limited and qualitative dependent-variables.
Prerequisites: None. All methods to be employed will be thoroughly, albeit quickly, introduced en route. A prior course in Linear Regression and Categorical Data Analysis or Maximum Likelihood Estimation is recommended.
EITM certification is available for graded course completion.
Fees: Consult the fee structure.
Location: ICPSR -- Ann Arbor, MI
Date(s): July 24 - August 18
Time: 10:00 AM - 12:00 PM