In this course, students will learn core statistical and computations principles that will allow them to perform quantitative analyses using social data. The course is designed for social science students at the beginning of their graduate school careers. However, advanced undergraduates can take the course, which will involve a few modifications to the assignment schedule.
Sociology 5811 will review basic probability, and then move on to univariate inference, the linear regression model, and introductory lessons of causal inference. In doing so, students will explore statistical concepts and methods that provide the foundation sociologists use to most commonly collect and analyze numerical evidence. Sociology 5811 will also provide the foundation for data management and statistical inference using Stata, a statistical computing environment that is popular in the social sciences. This course focuses on the practical application and substantive understanding of the linear regression models, rather than a full expounding of the mathematical details and statistical theory underlying these models. We will work closely with real data throughout the semester, which will also introduce students to the process of data management.
Understand the basic logic of statistical modeling.
Construct an appropriate model to appropriately address a research question.
Estimate and interpret linear regression models in Stata.
Write clean, reproducible, legible code in Stata.
Communicate results from multiple regression analyses for a broad audience.
Become familiar with visualizing multivariate relationships and presenting regression output in professional tables.