Regression Discontinuity Designs - Online Course
A 3-Day Livestream Seminar Taught by
Gonzalo Vazquez-Bare10:00am-12:30pm (convert to your local time)
1:30pm-3:30pm
This course covers the statistical foundations and practical applications of Regression Discontinuity (RD) designs. Many treatments or policies are administered when a score exceeds a pre-specified cutoff. For example, a university scholarship may be granted to students whose entry exam score is higher than a certain value, a government anti-poverty program may be made available to households with a poverty index beyond a certain level, or a drug may be given when a patient’s blood pressure exceeds a threshold.
In such settings, an RD design is based on comparing treated units slightly above the cutoff to untreated units slightly below it to estimate the effect of this treatment without relying on parametric, functional form, or distributional assumptions. The RD design has become a very popular tool for causal inference and is used widely in economics, political science, education, sociology, health sciences, environmental sciences and many other areas.
This course will cover foundational concepts and recent advances in identification, estimation, and statistical inference for RD models.
Starting January 11, this seminar will be presented as a 3-day synchronous, livestream workshop via Zoom. Each day will feature two lecture sessions with hands-on exercises, separated by a 1-hour break. Live attendance is recommended for the best experience. But if you can’t join in real time, recordings will be available within 24 hours and can be accessed for four weeks after the seminar.
Closed captioning is available for all live and recorded sessions. Live captions can be translated to a variety of languages including Spanish, Korean, and Italian. For more information, click here.
ECTS Equivalent Points: 1
More details about the course content
After taking this seminar, you will have the skills to:
-
- Estimate causal effects in RD designs and conduct data-driven bandwidth selection without making parametric modeling assumptions.
- Interpret the estimated effects from RD designs and the assumptions behind them.
- Provide empirical support for the validity of the identification assumptions behind RD models and conduct sensitivity analysis to assess the robustness of the estimation results.
After taking this seminar, you will have the skills to:
-
- Estimate causal effects in RD designs and conduct data-driven bandwidth selection without making parametric modeling assumptions.
- Interpret the estimated effects from RD designs and the assumptions behind them.
- Provide empirical support for the validity of the identification assumptions behind RD models and conduct sensitivity analysis to assess the robustness of the estimation results.
Computing
The topics discussed in the course will be illustrated with hands-on, in-class empirical applications using R. The corresponding Stata code will also be made available.
We will use a collection of software packages specifically designed to incorporate these recent advances in RD into the empirical practice. R and Stata versions of these packages, together with illustration manuals, replication code, and datasets, can be downloaded from: https://rdpackages.github.io/.
You should be able to conduct some basic data manipulation and statistical analysis using either R or Stata.
If you’d like to use R for this course but don’t yet have much experience with that package, here are some excellent on-line resources for building your R skills.
If you’d like to use Stata for this course but don’t yet have much experience with that package, we recommend following along with a “getting started” video like the one here.
Seminar participants who are not yet ready to purchase Stata could take advantage of StataCorp’s free 30-day evaluation offer or their 30-day software return policy.
The topics discussed in the course will be illustrated with hands-on, in-class empirical applications using R. The corresponding Stata code will also be made available.
We will use a collection of software packages specifically designed to incorporate these recent advances in RD into the empirical practice. R and Stata versions of these packages, together with illustration manuals, replication code, and datasets, can be downloaded from: https://rdpackages.github.io/.
You should be able to conduct some basic data manipulation and statistical analysis using either R or Stata.
If you’d like to use R for this course but don’t yet have much experience with that package, here are some excellent on-line resources for building your R skills.
If you’d like to use Stata for this course but don’t yet have much experience with that package, we recommend following along with a “getting started” video like the one here.
Seminar participants who are not yet ready to purchase Stata could take advantage of StataCorp’s free 30-day evaluation offer or their 30-day software return policy.
Who should register?
This course is designed for empirical researchers interested in conducting data analysis for causal inference and policy evaluation. While the course will be as self-contained as possible, you are expected to have a solid working knowledge of statistics (including sampling, expectation, variance and covariance, hypothesis testing, confidence intervals, standard error estimation) and multivariate linear regression.
This course is designed for empirical researchers interested in conducting data analysis for causal inference and policy evaluation. While the course will be as self-contained as possible, you are expected to have a solid working knowledge of statistics (including sampling, expectation, variance and covariance, hypothesis testing, confidence intervals, standard error estimation) and multivariate linear regression.
Seminar outline
Day 1:
- Potential outcomes, causal effects, and brief review of randomized experiments
- Introduction to RD models: graphical representation, identification, and interpretation
Day 2:
- Continuity-based analysis: estimation, bandwidth selection, statistical inference
- Falsification analysis, density continuity tests, inclusion of covariates
- Fuzzy RD designs
Day 3:
- Local randomization analysis and randomization inference
- RD with a discrete running variable
- Multicutoff and multiscore RD, geographic RD
Day 1:
- Potential outcomes, causal effects, and brief review of randomized experiments
- Introduction to RD models: graphical representation, identification, and interpretation
Day 2:
- Continuity-based analysis: estimation, bandwidth selection, statistical inference
- Falsification analysis, density continuity tests, inclusion of covariates
- Fuzzy RD designs
Day 3:
- Local randomization analysis and randomization inference
- RD with a discrete running variable
- Multicutoff and multiscore RD, geographic RD
Payment information
The fee of $995 includes all course materials.
PayPal and all major credit cards are accepted.
Our Tax ID number is 26-4576270.
The fee of $995 includes all course materials.
PayPal and all major credit cards are accepted.
Our Tax ID number is 26-4576270.