Session title: Causal Inference for Complex Data

Session Abstract: Mediation and confounding are fundamental concepts in causal inference research across various disciplines. Understanding the intricate relationships among these concepts is crucial for accurate interpretation of research findings and for making informed decisions in policy, healthcare, social sciences, and beyond. This session aims to explore the interplay between causal inference, mediation analysis, and confounding, providing attendees with practical insights, methodologies, and tools to navigate these complexities effectively.

Session Objectives: Provide an overview of causal inference and its significance in research. Discuss the concept of mediation and its role in elucidating causal pathways. Examine various methods for assessing and addressing confounding variables. Explore practical applications of causal inference, mediation analysis, and confounding control across different domains. Discuss challenges and best practices in conducting causal inference research.

Proposed Speakers: 
Oliver Dukes, Assistant Professor, Ghent University 
Feng Liang, Ph.D. candidate, Beijing Normal University
Mats Julius Stensrud, Assistant Professor, EPFL 
Lixing Zhu, Professor, Beijing Normal University
Ruoqing Zhu, Associate Professor, UIUC 

Audience: This session targets researchers, practitioners, policymakers, and students interested in advancing their understanding of causal inference, mediation analysis, and confounding control. Participants from diverse fields such as statistics, epidemiology, public health, social sciences, economics, and data science are encouraged to attend.