Principles of Causal Inference

Ziele

Causal inference has spawned renewed interest as a formal framework for answering scientific questions across many domains, spanning epidemiology, economics, medicine, artificial intelligence and more. Understanding and predicting the effect of interventions is a fundamental component of effective policy and decision-making. The ultimate goal of a majority of scientific studies is to establish if and how changing certain conditions, policies, practices and behaviours will affect given outcomes of interest.

Questions about the consequences of an action are causal in nature. They are, therefore, best tackled within a causal inference framework, aiming to go beyond predictions to make causal predictions. Where appropriate, explicitly framing study questions with causal language has several advantages over common analytical approaches: it adds to the transparency of the objectives and the underlying structural assumptions, and it helps with the interpretation and clarification of the potential limitations of any analysis.

By reasoning about causality with directed acyclic graphs (DAGs) and describing data-generating mechanisms with causal diagrams, we can further enhance/improve the communications between scientific investigators, analysts and other stakeholders. Especially in the context of real-world data analysis, causal inference offers a coherent framework to strengthen the quality of the conclusions we can draw from quantitative analyses of empirical evidence to inform and guide decisions which carry the potential to impact society.

The course proposes itself as a gentle introduction to causal thinking, aiming to provide the key concepts and principles of causal inference, touching upon some of the most common tools for causal inference. Target audience: researchers new to causal reasoning who wish to familiarize themselves with the causal language and grasp the foundational concepts for delving into the causal inference literature.

Kursinhalte

Formulating research questions in the language of causal inference. Defining causal effects.
Introducing the identifiability assumptions for making causal inference from observational data.
Reasoning about causality and describing data-generating mechanisms with causal diagrams.
Identifying potential sources of bias with the help of graphical criteria to inform the study design and analysis.

Form

Presentation of concepts by the instructor followed by discussions and group work.
Lecture slides will be made available during the course, together with suggested readings and references.

Adressatinnen und Adressaten

All Doctoral Candidates

Informationen zu den Dozierenden

The instructor for this workshop is Giusi Moffa, assistant professor of Statistics at the Department of Mathematics and Computer Science of the University of Basel, with expertise in the development of statistical methods for causal discovery and techniques for estimating intervention effects from observational data. Her methodological work is motivated by real-life problems in health care, clinical research and epidemiology, with consolidated experience in the implementation of data analyses supporting scientific research across diverse disciplines.

Leistungsspektrum / Workload

Total of 30 hours (preliminary readings 6h, 2x 8h attendance, follow-up work 8h)

Besonderheiten

Once registration is open, applications will be collected for 24 hours and course places allocated by lot. All registrations received after the initial 24h period will be put on a waiting list and assigned on a first come, first served basis.

Course places/places on the waiting list will be confirmed by e-mail. Course registrations can only be canceled before the registration period ends (send an e-mail to grace@unibas.ch). Full course attendance is mandatory. Participants who fail to attend a course without prior notification or withdraw after the registration deadline are subject to a fee of CHF 30. In addition, participants who cancel their course registration at a later point in time, are absent without an excuse or do not attend the entire course will, for reasons of fairness, not be considered for course registration in the following semester and will be removed from other courses offered in the same semester. Please find the detailed regulations on the Transferable Skills Homepage.