Course Description
This course is the second course in applied statistical methods for social scientists. Building on the materials we covered in POL 572 or its equivalent (i.e., linear regression, structural equation modeling, instrumental variables, maximum likelihood estimation, discrete choice models), students will learn a variety of statistical methods including models for longitudinal data and survival data. Unlike traditional courses on applied regression modeling, I will emphasize the connections between these methods and causal inference, which is the primary goal of social science research. Prerequisite: POL 572 or equivalent.
Lecture Slides
- Quantitative Social Science at Princeton
- Discrete Choice Models : Ordered/Multinomial Logit/Probit Models, Sample Selection Model
- Applied Regression Models for Cross-Section Data: Event Count Models, Generalized Linear Models
- Causal Inference: Fixed Effects Regression, Difference-in-Differences, Matching, Propensity Score, Weighting, Doubly-robust Estimator, Missing Data
- Applied Regression Models for Longitudinal Data: Varying Intercept Models, Linear Mixed Effects Models, Generalized Linear Mixed Effects Models, Generalized Estimating Equations, Incidental Parameter Problem and Conditional Likelihood
- Survival Data Analysis: Basic Concepts, Nonparametric Estimation of Survival Function, Parametric Regression Models, Cox Proportional-Hazard Model, Competing Risks Models