Causal Inference

Our goal is to provide a clear and accessible understanding of how quasi-experimental methodology approximates the randomized control trials that have been used traditionally to reveal causality. A strong understanding of the assumptions that are required to make the inferences will be made explicit. Additionally, we will provide a thorough initial introduction into understanding the causal graphical models that are becoming more popular in the health and behavioral sciences. This workshop is designed to provide participants with the knowledge to determine which approach is most useful for revealing causal information for their research question.

Our workshop is designed for graduate students, post-doctoral fellows, faculty, and research scientists from the behavioral, social, and health sciences. Although it is recommended that participants have a working knowledge of the general regression model, these core concepts will be reviewed at the beginning of the workshop. Participants who seek a more in depth review prior to attending may also wish to watch our Linear Regression Playlist on YouTube.

Chapter 1: General Introduction
1.1 Introduction to the Causal Modeling Process
1.2 Randomization and Experiments
1.3 Potential Outcomes Framework
1.4 Counterfactuals

Chapter 2: Differences-in-Differences Designs
2.1 Review of Linear Regression
2.2 Relationship to Analysis of Covariance
2.3 Extension to Differences-in-Differences-in-Differences
2.4 Synthetic Controls

Chapter 3: Regression Discontinuity Designs
3.1 Introduction to the Standard Regression Discontinuity
3.2 Fuzzy Regression Discontinuity
3.3 Inference in Regression Discontinuity

Chapter 4: Longitudinal Causality
4.1 Piecewise Regression
4.2 Interrupted Time Series
4.2 Granger Causality

Chapter 5: Propensity Scores
5.1 Estimation via Logistic Regression
5.2 Matching Methods
5.3 Propensity Scores as Weights
5.4 Propensity Score Subclassification

Chapter 6: Graphical Models
6.1 Mediation Models
6.2 Directed Acyclic Graphs
6.3 Identification of Causal Effects
6.4 Search for Causal Graphical Models

Livestream lectures will begin at 10:00 a.m. and finish at approximately 3:30 p.m. Eastern Time (US) each day. There will be 10-minute morning and afternoon breaks and a one-hour lunch break, the exact times of which are determined during lecture. Local time zones within which the participant is connected must be adjusted to correspond to Eastern Time (US).

Demonstrations will be conducted live in R. Note that R can be downloaded for free. While it is helpful to have some familiarity with R, this is not necessary. The lectures for the workshop are software-independent.

Doug Steinley teaches the workshop live via Zoom with recordings posted at the end of each day for those who might miss or wish to review any of the material. Demonstrations are interwoven with lectures and conducted using the R statistical software program. Note that R can be downloaded for free.

Participants receive access to the livestream, one-year of access to recorded lecture and demonstration videos, downloadable complete PDF copies of the course notes and software demonstrations, as well as data and code for all examples. The PDFs are not time-limited and may be retained indefinitely but should not be distributed to others without obtaining prior permission.