Causal Effects via DAGs | How to Handle Unobserved Confounders

Показать описание

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.

Resources:

--

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

Рекомендации по теме

Комментарии

In 11:20, when listing the back door paths from Z2 to Y. Aren't you missing the path Z2 <- Z4 -> Y?

ketalesto

I know in your Causal Discovery video you explained how to find a causal model using data alone. And to find Causal Inferences, you have to generate an estimand. However, while using these techniques in a social research, can we determine a DAG on our own hypothesis? Or using other qualitative observational data? Can the DAG be purely human made?

veerajakamthe

Regarding 11:30 - I don't quite understand why the path is blocked by X? Wouldn't it only be blocked by X if we would condition on it (or if it was a collider)?

Shayan

5:01 Why is "X ← Z1 → Z3 ← Z2→ Y" also a back door path, as Z3 doesn't point to Z2?

karannchew

Hello! I have a reference saying this: "If the causal graph doesn’t contain cycles but the noise terms are dependent, then the model is semi-Markovian. ... Finally, the graphs of non-Markovian models contain cycles." May I clarify in 4:00 if you meant Semi-Markovian? Thanks a lot. I just have so many questions cause I'm really confused with all my readings, so I'm relying on your videos for simplification.

norhanifahcali-lsxr

An idea for future video. On applying CI to time series data.

wryltxw

Causal Effects via DAGs | How to Handle Unobserved Confounders

Causal Effects via DAGs | How to Handle Unobserved Confounders

Building and Using DAGs for Causal Inference

Causal Effects via the Do-operator | Overview & Example

Directed Acyclic Graphs (DAGs)

PMAP 8521 • (4) Measurement and DAGs: (2) Causal models

PMAP 8521 • (4) Measurement and DAGs: (3) Paths, doors, and adjustment

Causal Effects via Regression w/ Python Code

Identifying causal effects in maximally oriented partially directed acyclic graphs

Emilija Perkovic: Causal effects in maximally oriented partially directed acyclic graphs (MPDAGs)

Part 4—Directed Acyclic Graphs (DAGs) for Causal Inference in Tobacco Research

What is DAG?

Causal Effects via Propensity Scores | Introduction & Python Code

Johannes Textor: Causal Inference using the R package DAGitty

Causal DAGs 101

4.6 - The Backdoor Adjustment

An Introduction to Potential Outcomes, DAGs and Single-World Intervention Graphs

CECTR Webinar Series Part 4—Directed Acyclic Graphs (DAGs) for Causal Inference in Tobacco Research...

Causal Effects | An introduction

Causal Inference - EXPLAINED!

How Markov assumption links DAG to data

Introduction to Causal Inference and Directed Acyclic Graphs

Selection Bias Graphically - Causal Inference

Estimating Causal Effects: Regression

Richard Guo - Seminar - 'Possible Causal Effects: Enumeration and Estimation'