The Book of Why

Judea Pearl

Not very engaging but definitely important topic of correlation, causation, statistics and AI.


I read ~30% of the book normally and the rest as blinks.

With the diagrams it is possible to tell why. To move from correlation to causality.

Three ladders.

CLippings

The Book of Why (Judea Pearl)

The new science does not have a fancy name: I call it simply “causal inference,”

The Book of Why (Judea Pearl)

Why? Causal inference is all about taking this question seriously.

The Book of Why (Judea Pearl)

the founders of modern statistics, Francis Galton and Karl Pearson,

The Book of Why (Judea Pearl)

mathematicians like Blaise Pascal (1654), Pierre de Fermat (1654), and Christiaan Huygens (1657) find it necessary to develop what we today call probability theory.

The Book of Why (Judea Pearl)

mathematicians like Edmond Halley (1693) and Abraham de Moivre (1725) begin looking at mortality tables to calculate life expectancies.

The Book of Why (Judea Pearl)

Jacob Bernoulli, Pierre-Simon Laplace, and Carl Friedrich Gauss to develop a theory of errors to help us extract signals from noise.

The Book of Why (Judea Pearl)

when you prohibit speech, you prohibit thought

The Book of Why (Judea Pearl)

index of a statistics textbook for an entry on “cause.” Students are not allowed to say that X is the cause of Y—only that X and Y are “related” or “associated.”

The Book of Why (Judea Pearl)

Students are not allowed to say that X is the cause of Y—only that X and Y are “related” or “associated.”

The Book of Why (Judea Pearl)

geneticist Sewall Wright in the 1920s and a direct ancestor of the methods we will entertain in this book.

The Book of Why (Judea Pearl)

data are profoundly dumb. Data can tell you that the people who took a medicine

The Book of Why (Judea Pearl)

data are profoundly dumb.

The Book of Why (Judea Pearl)

Seeing the barometer fall increases the probability of the storm, while forcing it to fall does not affect this probability.

The Book of Why (Judea Pearl)

Two people who share the same causal model will also share all counterfactual judgments.

The Book of Why (Judea Pearl)

You cannot answer a question that you cannot ask, and you cannot ask a question that you have no words for.

The Book of Why (Judea Pearl)

data are profoundly dumb about causal relationships.

The Book of Why (Judea Pearl)

you are smarter than your data.

The Book of Why (Judea Pearl)

there is no better way to understand ourselves than by emulating ourselves.

The Book of Why (Judea Pearl)

God asked “what,” and they answered “why.”

The Book of Why (Judea Pearl)

the vertical line means “given that you see.”

The Book of Why (Judea Pearl)

deep learning has succeeded primarily by showing that certain questions or

The Book of Why (Judea Pearl)

deep learning has succeeded primarily by showing that certain questions or tasks we thought were difficult are in fact not.

The Book of Why (Judea Pearl)

the field of artificial intelligence is “bursting with microdiscoveries”—the

The Book of Why (Judea Pearl)

Democritus (460–370 BC) said, “I would rather discover one cause than be the King of Persia.”

The Book of Why (Judea Pearl)

Computers are not good at breaking rules, a skill at which children excel.

The Book of Why (Judea Pearl)

Very often the structure of the diagram itself enables us to estimate all sorts of causal and counterfactual relationships: simple or complicated,

The Book of Why (Judea Pearl)

Very often the structure of the diagram itself enables us to estimate all sorts of causal and counterfactual relationships: simple or complicated,

The Book of Why (Judea Pearl)

Very often the structure of the diagram itself enables us to estimate all sorts of causal and counterfactual relationships: simple or complicated, deterministic or probabilistic, linear or nonlinear.

The Book of Why (Judea Pearl)

in both a cognitive and a philosophical sense, the idea of causes and effects is much more fundamental than the idea of probability.

The Book of Why (Judea Pearl)

estimate for our query. It is because of this robustness, I conjecture, that human intuition is organized around causal, not

The Book of Why (Judea Pearl)

It is because of this robustness, I conjecture, that human intuition

The Book of Why (Judea Pearl)

It is because of this robustness, I conjecture, that human intuition

The Book of Why (Judea Pearl)

new data and produce a new estimate for our query. It is because of this robustness, I conjecture, that human intuition is organized around causal, not statistical, relations.

The Book of Why (Judea Pearl)

new data and produce a new estimate for our query. It is

The Book of Why (Judea Pearl)

It is because of this robustness, I conjecture, that human intuition is organized around causal, not statistical, relations.

The Book of Why (Judea Pearl)

while probabilities encode our beliefs about a static world, causality tells us whether and how probabilities change when the world changes, be it by intervention or by act of imagination.

The Book of Why (Judea Pearl)

“Success = talent + luck.

The Book of Why (Judea Pearl)

“Success = talent + luck. Great success = a little more talent + a lot of luck.”

The Book of Why (Judea Pearl)

Scientists will always prefer routine calculations on data to methods that challenge their scientific knowledge.

The Book of Why (Judea Pearl)

Scientists will always prefer routine calculations on data to methods that challenge their scientific knowledge.

The Book of Why (Judea Pearl)

Scientists will always prefer routine calculations on data to methods that challenge their scientific knowledge.

The Book of Why (Judea Pearl)

Fisher was right about one point: once you remove causation from statistics, reduction of data is the only thing left.

The Book of Why (Judea Pearl)

David Rumelhart, a cognitive scientist at University of California, San Diego,

The Book of Why (Judea Pearl)

Bayes’s rule tells us how to reverse the procedure, specifically by multiplying the prior probability by a likelihood ratio.

The Book of Why (Judea Pearl)

Although we call them “fire alarms,” they are really smoke alarms.

The Book of Why (Judea Pearl)

Hans Reichenbach, a German-American philosopher of science.)

The Book of Why (Judea Pearl)

For example, we cannot distinguish the fork A B C from the chain A B C by data alone, because the two

The Book of Why (Judea Pearl)

For example, we cannot distinguish the fork A B C from the chain A B C by data alone, because the two diagrams imply the same independence conditions.

The Book of Why (Judea Pearl)

If you choose a diet based only on one friend’s experience, you are essentially saying that you believe you are similar to your friend in all relevant details: age, heredity, home environment, previous diet, and so forth.

The Book of Why (Judea Pearl)

Nature is like a genie that answers exactly the question we pose, not necessarily the one we intend to ask. But

The Book of Why (Judea Pearl)

Nature is like a genie that answers exactly the question we pose, not necessarily the one we intend to ask.

The Book of Why (Judea Pearl)

Fisher realized that an uncertain answer to the right question is much better than a highly certain answer to the wrong question.

December 19, 2020 |