A 3-Day Remote Seminar Taught by
Felix Elwert, Ph.D.
To see a sample of the course materials, click here.
This course offers an in-depth survey of modern instrumental variables (IV) analysis. IV analysis is an important quasi-experimental technique with numerous applications in economics, the social and biomedical sciences, business, marketing, and education.
IVs allow us to get unbiased estimates of causal effects even when there is selection bias, unobserved confounding, or imperfect compliance. The technique applies equally to randomized trials and observational studies. IV analysis is a very powerful tool—as long as the underlying assumptions are met.
Starting February 25, we are offering this seminar as a 3-day synchronous*, remote workshop for the first time. Each day will consist of a 4-hour live lecture held via the free video-conferencing software Zoom. You are encouraged to join the lecture live, but will have the opportunity to view the recorded session later in the day if you are unable to attend at the scheduled time.
Each lecture session will conclude with a hands-on exercise reviewing the content covered, to be completed on your own. An additional session will be held Thursday and Friday afternoons as an “office hour”, where you can review the exercise results with the instructor and ask any questions.
*We understand that scheduling is difficult during this unpredictable time. If you prefer, you may take all or part of the course asynchronously. The video recordings will be made available within 24 hours of each session and will be accessible for two weeks after the seminar, meaning that you will get all of the class content and discussions even if you cannot participate synchronously.
MORE DETAILS ABOUT THE COURSE CONTENT
This seminar will take you from the basic Wald estimator up to powerful recent developments, including non-parametric tests of the exclusion assumption. You will get extensive hands-on experience by analyzing real world examples across the social sciences. We will carefully dissect key technical and substantive assumptions to empower you to recognize, understand, and empirically test these assumptions in practice.
This seminar puts a premium on a practical understanding. We will capitalize on three complementary perspectives: modern potential-outcomes notation, visually intuitive directed acyclic graphs (DAGs), and the traditional algebraic approach. This will enable you to recognize IVs in your own studies, understand assumptions thoroughly, and read the specialist literatures in different fields.
Topics include single instruments, multiple instruments, weak instruments, first-stage diagnostics, over-identification tests, exclusion tests, two-stage least squares (2SLS), natural experiments, encouragement trials, Mendelian randomization, continuous and categorical outcomes, compliance classes, local average treatment effects (LATE), and Balke-Pearl bounds.
We will use the latest commands in Stata and learn theoretical and practical insights that transfer across software packages.
This remote seminar is held via Zoom, a free video conferencing application. Instructions for joining a session via Zoom are available here. Before the seminar begins, you will receive an email with the meeting code and password you must use to join.
This is a hands-on course with instructor-led software demonstrations and guided exercises. You should use a computer with a recent version of Stata installed (release 13 or later).
WHO SHOULD Register?
If you want to understand how and when you use instrumental variables analysis in practice, this course is for you. The material is equally applicable to experimental and non-experimental data. You should have a good working knowledge of multiple regression and basic knowledge of Stata (point-and-click graphical user interface or basic command line operation).
This course is appropriate for researchers (in industry or at universities, faculty, doctoral students, and advanced masters students) with a solid applied background in multiple regression analysis. This course does not require calculus. You will be given fully executable do-files, so no prior programming experience is necessary.
1. Causal effects
a. ATE: Average treatment effects
b. LATE: Local average treatment effects
c. Identification in randomized trials and observational studies
d. Problems: Confounding, selection, and attrition bias
2. Approaches to IV analysis
a. Potential outcomes
b. Directed acyclic graphs
a. Wald estimator (IV)
b. Two-stage least squares (TSLS)
c. Generalized methods of moments (GMM)
d. Limited information maximum likelihood (LIML)
e. Linear and nonlinear outcome models
f. Standard errors
g. Why one should never control for an IV in OLS
4. Understanding assumptions and their consequences
a. Weak instruments
b. Instrument ignorability
c. Instrument exclusion
5. Testing assumptions
a. Endogeneity tests
b. Over-identification tests
c. Balke-Pearl check
“Felix excels at making abstract and complicated ideas accessible to a general audience by combining them with concrete, real-life examples. As a statistician, I feel that I learned a lot from his lecture by viewing statistical models and methods from applied perspectives.”
Lu Mao, University of Wisconsin, Madison
“Felix is an amazing instructor. He is very knowledgeable on the topic and is also very passionate about the subject. He explains the materials very clearly and I am even thinking of taking this course again.”
Carmen Tekwe, Texas A&M University
“I am very pleased by this course and the amount I learned in just two days exceeded my expectations. Elwert clearly masters all technical knowledge on this subject, and combines it with sound knowledge on application. Moreover, Elwert is very pedagogical and patiently answers all questions. I would definitely recommend this course to colleagues.”
Tarjei Widding-Havneraas, Haukeland University Hospital
“Highly recommend this interactive, informative course. Felix is an excellent teacher. Beneficial to all researchers, both applied and theoretical.”
Rachel Pownall, Maastricht University