O'Reilly logo

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required


Book Description

Can drinking coffee help people live longer? What makes a stock’s price go up? Why did you get the flu? Causal questions like these arise on a regular basis, but most people likely have not thought deeply about how to answer them.

This book helps you think about causality in a structured way: What is a cause, what are causes good for, and what is compelling evidence of causality? Author Samantha Kleinberg shows you how to develop a set of tools for thinking more critically about causes. You’ll learn how to question claims, identify causes, make decisions based on causal information, and verify causes through further tests.

Whether it’s figuring out what data you need, or understanding that the way you collect and prepare data affects the conclusions you can draw from it, Why will help you sharpen your causal inference skills.

Table of Contents

  1. Praise for Samantha Kleinberg’s Why
  2. Why
  3. Why: A Guide to Finding and Using Causes
  4. Preface
  5. 1. Beginnings
    1. Where do our concepts of causality and methods for finding it come from?
    2. What is a cause?
    3. How can we find causes?
    4. Why do we need causes?
    5. What next?
  6. 2. Psychology
    1. How do people learn about causes?
    2. Finding and using causes
      1. Perception
      2. Inference and reasoning
    3. Blame
    4. Culture
    5. Human limits
  7. 3. Correlation
    1. Why are so many causal statements wrong?
    2. What is a correlation?
      1. No correlation without variation
      2. Measuring and interpreting correlation
    3. What can we do with correlations?
    4. Why isn’t correlation causation?
    5. Multiple testing and p-values
    6. Causation without correlation
  8. 4. Time
    1. How does time affect our ability to perceive and reason with causality?
    2. Perceiving causality
    3. The direction of time
    4. When things change over time
    5. Using causes: It’s about time
    6. Time can be misleading
  9. 5. Observation
    1. How can we learn about causes just by watching how things work?
    2. Regularities
      1. Mill’s methods
      2. Complex causes
    3. Probabilities
      1. Why probability?
      2. From probabilities to causes
    4. Simpson’s paradox
    5. Counterfactuals
    6. The limits of observation
  10. 6. Computation
    1. How can the process of finding causes be automated?
    2. Assumptions
      1. No hidden common causes
      2. Representative distribution
      3. The right variables
    3. Graphical models
      1. What makes a graphical model causal?
      2. From data to graphs
    4. Measuring causality
      1. Probabilistic causal significance
      2. Granger causality
    5. Now what?
  11. 7. Experimentation
    1. How can we find causes by intervening on people and systems?
    2. Getting causes from interventions
    3. Randomized controlled trials
      1. Why randomize?
      2. How to control
      3. Who do results apply to?
    4. When n=you
    5. Reproducibility
    6. Mechanisms
    7. Are experiments enough to find causes?
  12. 8. Explanation
    1. What does it mean to say that this caused that?
    2. Finding causes of a single event
      1. When multiple causes occur
      2. Explanations can be subjective
      3. When did the cause happen?
    3. Explanation with uncertainty
    4. Separating type and token
    5. Automating explanation
    6. Causality in the law
      1. But-for causes
      2. Proximate causes
      3. Juries
  13. 9. Action
    1. How do we get from causes to decisions?
    2. Evaluating causal claims
      1. Strength
      2. Consistency (repeatability)
      3. Specificity
      4. Temporality
      5. Biological gradient
      6. Plausibility and Coherence
      7. Experiment
      8. Analogy
    3. From causes to policies
      1. Context
      2. Efficacy and effectiveness
      3. Unintended consequences
  14. 10. Onward
    1. Why causality now?
    2. The need for causality
    3. Key principles
      1. Causation and correlation are not synonymous
      2. Think critically about bias
      3. Time matters
      4. All experimentation is not better than all observation
    4. A well-stocked toolbox
    5. The need for human knowledge
  15. Acknowledgments
  16. A. Notes
    1. Chapter 1. Beginnings
    2. Chapter 2. Psychology
    3. Chapter 3. Correlation
    4. Chapter 4. Time
    5. Chapter 5. Observation
    6. Chapter 6. Computation
    7. Chapter 7. Experimentation
    8. Chapter 8. Explanation
    9. Chapter 9. Action
    10. Chapter 10. Onward
  17. Bibliography
  18. Index
  19. About the Author
  20. Colophon