Reader small image

You're reading from  Causal Inference and Discovery in Python

Product typeBook
Published inMay 2023
PublisherPackt
ISBN-139781804612989
Edition1st Edition
Concepts
Right arrow
Author (1)
Aleksander Molak
Aleksander Molak
author image
Aleksander Molak

Aleksander Molak is a Machine Learning Researcher and Consultant who gained experience working with Fortune 100, Fortune 500, and Inc. 5000 companies across Europe, the USA, and Israel, designing and building large-scale machine learning systems. On a mission to democratize causality for businesses and machine learning practitioners, Aleksander is a prolific writer, creator, and international speaker. As a co-founder of Lespire, an innovative provider of AI and machine learning training for corporate teams, Aleksander is committed to empowering businesses to harness the full potential of cutting-edge technologies that allow them to stay ahead of the curve.
Read more about Aleksander Molak

Right arrow

Are there other criteria out there? Let’s do-calculus!

In the real world, not all causal graphs will have a structure that allows the use of the back-door or front-door criteria. Does this mean that we cannot do anything about them?

Fortunately, no. Back-door and front-door criteria are special cases of a more general framework called do-calculus (Pearl, 2009). Moreover, do-calculus has been proven to be complete (Shpitser and Pearl, 2006), meaning that if there is an identifiable causal effect in a given DAG, <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math"><mml:mi>G</mml:mi></mml:math>, it can be found using the rules of do-calculus.

What are these rules?

The three rules of do-calculus

Before we can answer the question, we need to define some new helpful notation.

Given a DAG <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math"><mml:mi>G</mml:mi></mml:math>, we can say that <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math"><mml:msub><mml:mrow><mml:mi>G</mml:mi></mml:mrow><mml:mrow><mml:mover accent="true"><mml:mrow><mml:mi>X</mml:mi></mml:mrow><mml:mo>-</mml:mo></mml:mover></mml:mrow></mml:msub></mml:math> is a modification of <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math"><mml:mi>G</mml:mi></mml:math>, where we removed all the incoming edges to the <math xmlns="http://www.w3.org/1998/Math/MathML"><mrow><mrow><mi mathvariant="normal">n</mi><mi mathvariant="normal">o</mi><mi mathvariant="normal">d</mi><mi mathvariant="normal">e</mi><mi>X</mi></mrow></mrow></math>. We will call <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math"><mml:msub><mml:mrow><mml:mi>G</mml:mi></mml:mrow><mml:mrow><mml:munder underaccent="false"><mml:mrow><mml:mi>X</mml:mi></mml:mrow><mml:mo>_</mml:mo></mml:munder></mml:mrow></mml:msub></mml:math> a modification of <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math"><mml:mi>G</mml:mi></mml:math>, where we removed all the outgoing edges from the node <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math"><mml:mi>X</mml:mi></mml:math>.

For example, <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math"><mml:msub><mml:mrow><mml:mi>G</mml:mi></mml:mrow><mml:mrow><mml:mover accent="true"><mml:mrow><mml:mi>X</mml:mi></mml:mrow><mml:mo>-</mml:mo></mml:mover><mml:munder underaccent="false"><mml:mrow><mml:mi>Z</mml:mi></mml:mrow><mml:mo>_</mml:mo></mml:munder></mml:mrow></mml:msub></mml:math> will denote a DAG, <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math"><mml:mi>G</mml:mi></mml:math>, where we removed all the incoming edges to the...

lock icon
The rest of the page is locked
Previous PageNext Page
You have been reading a chapter from
Causal Inference and Discovery in Python
Published in: May 2023Publisher: PacktISBN-13: 9781804612989

Author (1)

author image
Aleksander Molak

Aleksander Molak is a Machine Learning Researcher and Consultant who gained experience working with Fortune 100, Fortune 500, and Inc. 5000 companies across Europe, the USA, and Israel, designing and building large-scale machine learning systems. On a mission to democratize causality for businesses and machine learning practitioners, Aleksander is a prolific writer, creator, and international speaker. As a co-founder of Lespire, an innovative provider of AI and machine learning training for corporate teams, Aleksander is committed to empowering businesses to harness the full potential of cutting-edge technologies that allow them to stay ahead of the curve.
Read more about Aleksander Molak