Skip to content
Back to Instructors

Stephen Vaisey

Director of AI Horizons

Stephen Vaisey, Ph.D., is Professor of Sociology and Political Science and the Director of the Worldview Lab at Duke University. He specializes in the use of survey data to measure cultural differences and cultural change.

Professor Vaisey completed his Ph.D. at the University of North Carolina at Chapel Hill in 2008. He was an assistant professor at the University of California, Berkeley before moving to Duke University in 2011. He has published papers in the American Journal of Sociology, the American Sociological ReviewSocial Forces, and other top journals.

His substantive research focuses on the measurement, origins, and consequences of moral and political differences. He has also published on the benefits and limitations of using panel data for causal inference.

Vaisey has taught applied statistics courses at the graduate level for over a decade. He takes great pleasure in helping people gain an intuitive and practical understanding of statistical methods and has received outstanding reviews for his teaching.

He also teaches seminars for AI Horizons, where he offers training on using LLM workflows for longitudinal and multilevel models.

You can visit his university webpage here.

Google Scholar Citation Page

 

Stephen's Seminars
Livestream

Longitudinal Data Analysis Using R

The most common type of longitudinal data is panel data or repeated measures data, consisting of measurements of predictor and response variables at two or more points in time for many individuals (or other units). Panel data enable two major advances over cross-sectional...

View Details
Livestream

Multilevel and Mixed Models Using R

Multilevel models are a class of regression models for data that have a hierarchical (or nested) structure. Common examples of such data structures are students nested within schools or classrooms, patients nested within hospitals, or survey respondents nested within countries.

View Details
Livestream

Multilevel and Mixed Models with Stata and LLMs*

This seminar provides an intensive introduction to multilevel and mixed models, a class of regression models for data that have a hierarchical (or nested) structure. Common examples of such data structures are students nested within classrooms, patients nested within hospitals,...

View Details
On-Demand

Treatment Effects Analysis

This seminar focuses on matching and weighting cross-sectional observational data to obtain better causal estimates of treatment effects. The most common technique for estimating such effects is propensity score matching. We will cover this technique but you’ll soon see that it is just the tip of...

View Details