Causal Effects via DAGs | How to Handle Unobserved Confounders

This is the 4th video in a series on causal effects. In the last video, we saw that we could evaluate any causal effect for a Markovian causal model. However, the question remained of how to handle models that are not Markovian. In this video, we start to answer this question via two quick-and-easy graphical criteria for evaluating causal effects.

Series Playlist:    • Causality  
Blog: https://towardsdatascience.com/causal...

Resources:
- An Introduction to Causal Inference by Judea Pearl: https://www.degruyter.com/document/do...
- On Identifying Causal Effects by Tian & Shiptser: https://faculty.sites.iastate.edu/jti...

--
Book a call: https://calendly.com/shawhintalebi
Homepage: https://shawhintalebi.com/

Socials
  / shawhin  
  / shawhintalebi  
  / shawhint  
  / shawhintalebi  

The Data Entrepreneurs
🎥 YouTube:    / @thedataentrepreneurs  
👉 Discord:   / discord  
📰 Medium:   / the-data  
📅 Events: https://lu.ma/tde
🗞️ Newsletter: https://the-data-entrepreneurs.ck.pag...

Support ❤️
https://www.buymeacoffee.com/shawhint

Introduction - 0:00
Identifiability - 0:28
Markovian Models - 2:12
Unobserved Confounders - 3:19
Back & Front Door Criteria - 4:18
Back Door Path - 4:44
Blocking - 5:22
Back Door Criterion - 7:27
Front Door Criterion - 9:14