Applied Causal Inference for Data Science

Published in Columbia University, Department of Computer Science, 2024

This is an introductory and applied course in Casual Inference .

Topics Covered

Chapter 1: AB Testing
Chapter 2: Infrastructure and experiment implementation:
Chapter 3: Context: data science in business and observational data to guide policy decisions;
Chapter 4: Causal Frameworks:
Chapter 5: Intuition for the Pearlian Framework
Chapter 6: Identifiability and the Pearlian Framework
Chapter 7: From Probabilities to Data: Intro to conditioning
Chapter 8: Model-Based Conditioning
Chapter 9: Machine-learning Based Conditioning
Chapter 10: Limitations of Conditioning
Chapter 11: Instrumental Variables
Chapter 12: Mechanistic Inference
Chapter 13: Discontinuity Designs
Chapter 14: Panel Data Designs
Chapter 15: Context:
Chapter 16: Adjustment Methods

Math: Undergrad probability theory; Some experience with regression analysis will be useful; some knowledge of information theory will be useful, but not required. Some knowledge of bayesian networks will be useful but not required.
CS: Basic knowledge of Python and R