Machine Learning and AI Foundations: Causal Inference and Modeling

Course details

This course with instructor Keith McCormick provides an introduction to some advanced techniques in causal inference and causal modeling. It builds upon a foundation in Keith’s course, Machine Learning and AI Foundations: Prediction, Causality, and Statistical Inference. Keith focuses the course on three major topics: The power of experiments (and the reality that they aren't always available as an option); the Bayesian statistic philosophy and approach and when it's a good choice; and an introduction to causal modeling with techniques like structural equation modeling and Bayesian networks. Join Keith in this course to learn about these advanced techniques and what makes them both powerful and interesting.

Concepts

0. Introduction

01 - Thinking about causality
02 - What you should know

1. Experimental Design and Statistical Controls

03 - The investigator, the jury, and the judge
04 - Fisher and experiments
05 - John Snow and natural experiments
06 - Double blind studies
07 - Control variables (ANCOVA)
08 - Judea Pearl - Problems with control variables
09 - Moderation, mediation, and lurking variables
10 - Simpson's paradox
11 - Challenge - Moderation, mediation, or a third variable
12 - Solution - Moderation, mediation, or a third variable

2. Conditional Probability and Bayes' Theorem

13 - Turing, Enigma, and CAPTCHA
14 - Enigma and uncertainty
15 - Developing an intuition for Bayes with Wordle
16 - Wordle and conditional probability
17 - Wordle, bans, and bits
18 - Wordle and Bayes' theorem
19 - Challenge - Conditional probability and Bayes' theorem
20 - Solution - Conditional probability and Bayes' theorem

3. Prediction and Proof with Bayesian statistics

21 - Contrasting frequentist statistics and Bayesian statistics
22 - Bayesian T-Test with JASP
23 - Google Optimize
24 - Bayes and rare events
25 - Challenge - JASP
26 - Solution - JASP

4. Causal Modeling with Structural Equation Modeling (SEM)

27 - Sewell Wright
28 - Introducing path analysis and SEM
29 - SEM example - Intention
30 - Myths about SEM
31 - Latent variables in SEM
32 - Finding direction of causality with SEM (PSAT)

5. Causal Modeling with Bayesian Networks

33 - Judea Pearl and the causal revolution
34 - Downloading BayesiaLab and resources
35 - Introducing BayesiaLab - Hair and eye color
36 - Introduction to causal modeling with Bayesian networks
37 - Bayesian Networks - Black Swan case study

Conclusion

38 - Taking causality further

Machine Learning and AI Foundations: Causal Inference and Modeling

Authors

Keith McCormick