Announcing the 2023 Causal Inference Courses

Week One: Key Topics in Causal Inference

This 4-day course introduces concepts and methods for causal inference from observational data. Upon completion of the course, participants will be prepared to further explore the causal inference literature. Topics covered include the g-formula, inverse probability weighting of marginal structural models, causal mediation analysis, and methods to handle unmeasured confounding. The last day will end with a “capstone” open Q&A session with the instructors.

Instructors: Miguel Hernán, Judith Lok, James Robins, Eric Tchetgen Tchetgen & Tyler VanderWeele

Prerequisites: Participants are expected to be familiar with basic concepts in epidemiology and biostatistics, including linear and logistic regression and survival analysis techniques.

Audience: Researchers interested in acquiring a roadmap to navigate the literature on causal inference methods.

Week One: Advanced Confounding Adjustment

New! Causal inference from observational data often relies on appropriate adjustment for confounders. In this 4-day course, students will learn how to implement advanced g-methods for confounding adjustment—inverse probability weighting and the parametric g-formula—in increasingly complex analytical settings. The course introduces these methods in the context of a time-fixed treatment and extends them to the time-varying setting using a combination of lectures and hands-on sessions. All hands-on sessions will offer a choice between R and SAS. 

Instructors: Joy Shi, Barbra Dickerman, Miguel Hernán    Curriculum Fellows: Naiyu Chen, Alejandro Szmulewicz 

Prerequisites: Participants are expected to have experience with the analysis of health databases in academic or industry settings. Prior introductory coursework on study design and data analysis, working knowledge of R or SAS, and a laptop computer with R or SAS is required.

Audience: Researchers and analysts who want to acquire skills that are required for causal inference with time-varying treatments.

Week Two: Combining Information for Causal Inference

New! This 5-day course will provide hands-on training for causal inference by combining information from multiple and diverse sources. Students will learn concepts and methods for…

• Generalizability & transportability analyses that extend causal inferences from one or more randomized trials to a new target population
• External comparisons between an intervention examined in a single-group or comparative experimental study versus other interventions not examined in the experimental study
• Indirect comparisons of different experimental treatments evaluated in separate trials against a common control treatment
• General study design by leveraging novel matching and weighting methods that directly balance covariates

Emphasis will be on implementing the methods for causal research with randomized trial and real-world data. Through a combination of lectures and hands-on sessions, the course will introduce different settings for combining information and examine different examples of combining information in the health sciences. Students will learn how to carry out causal analyses using data from trials and healthcare databases (e.g., administrative claims and electronic health records). All sessions will be using R or SAS.

Instructors: Issa Dahabreh, José Zubizarreta    Curriculum Fellows: Sarah Robertson, Yu-Han Chiu, Eric Cohn

Prerequisites: Participants are expected to have experience with the analysis of health data in academic or industry settings. Prior introductory courses on study design and data analysis, working knowledge of R or SAS, and a laptop computer with R or SAS.

Audience: Researchers and analysts who want to use combinations of randomized trial and real-world data to learn what works.

Week Two: Target Trial Emulation

This 5-day course will provide hands-on training for causal inference using health databases. Students will learn the principles of target trial emulation and how to implement them for causal research with real-world data. Causal inference from observational data can be conceptualized as an attempt to emulate a pragmatic randomized trial—the target trial. Through a combination of lectures and hands-on sessions, the course introduces the target trial emulation framework in increasingly complex settings and dissects examples of emulations in the health sciences and related fields. Students will learn how to design target trial emulations and carry out appropriate causal analyses of healthcare databases such as administrative claims and electronic health records. All sessions will offer a choice between R and SAS.  

Instructors: Barbra Dickerman, Joy Shi, Miguel Hernán    Curriculum Fellows: Emma McGee, Lawson Ung 

Prerequisites: Participants are expected to have experience with the analysis of health databases in academic or industry settings. Prior introductory coursework on study design and data analysis, working knowledge of R or SAS, and a laptop computer with R or SAS is required. Participants must also either (i) complete the CAUSALab’s Advanced Confounding Adjustment course, or (ii) have equivalent prior knowledge of methods to adjust for confounding in the time-varying setting including inverse-probability weighting.

Audience: Researchers and analysts who use real-world databases to learn what works.