Regression discontinuity designs for evaluating programs and policies
August 20, 2024 2024-11-07 12:22Regression discontinuity designs for evaluating programs and policies
Overview of our regression discontinuity workshop
This workshop provides an introduction to the practical application of regression discontinuity design in evaluating programs and policies. Regression discontinuity (RD) is an observational research design which can be used to make causal inference of program effects in non-experimental situations. Regression discontinuity is applied when program treatments are allocated based upon a pre-determined rule. For example, if a remediation intervention is provided to all students who scored below a certain threshold on an academic aptitude exam, or, a financial subsidy is provided to all applicants with a household income falling below a particular value. A primary advantage of regression discontinuity designs is that causal effects can be estimated when program benefits are distributed based upon the subject’s need for the intervention, rather than randomization in the case of an experiment.
Expected outcomes
By the end of the workshop, participants will understand the advantages of regression discontinuity design, how to estimate regression discontinuity designs across a number of statistical packages, and how to use data to check the validity of these regression discontinuity estimates to make causal inference. Participants will learn both visual and statistical techniques to estimate and evaluate regression discontinuity treatment effects. Participants will learn both sharp regression discontinuity techniques (used when subjects are compliant with treatment intent) and fuzzy regression discontinuity techniques (when subjects are not compliant with treatment intent). Most importantly, participants will be ready to identify opportunities to evaluate programs and policies using regression discontinuity designs and will be prepared to estimate program effects using any statistical software package.
Who should attend?
The target audience for this workshop is a range of researchers, including institutional researchers, market researchers, policy analysts, student affairs professionals, assessment professionals, graduate students, and faculty, who evaluate programs in their work. It is important that participants have a working knowledge of ordinary least squares regression (OLS). If you don’t have a strong understanding of OLS, we encourage you to take our regression refresher workshop prior to enrolling in this workshop. Software demonstrations will use Stata, but R code will also be included for participants who are using R for their research projects.
Agenda
About the instructor
Serge Herzog, Ph.D., has been the Director, Office of Institutional Analysis, and Consultant, Center for Research Design & Analysis, University of Nevada, Reno since 2001. His research has been covered in the Chronicle of Higher Education, the University Business Magazine, and Campus Technology Magazine among others. Most recently, he co-edited (with Nicolas Bowman) Methodological Advances and Issues in Studying College Impact (New Directions for Institutional Research) San Francisco: Jossey-Bass, 2014.
