Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture delves into the concept of the front door criterion, explaining the conditions required for a valid adjustment set in causal inference. The instructor demonstrates how to derive the front door adjustment formula step by step, emphasizing the importance of using observable variables. Through a detailed example involving confounding variables and causal effects, the lecture illustrates how to apply the front door criterion to analyze the impact of attending a university on marital success. By combining the backdoor criterion with the front door criterion, the instructor showcases a comprehensive approach to causal inference, highlighting the significance of proper adjustment sets in drawing accurate causal conclusions.