An Intuitive Explanation of Eliezer Yudkowsky’s Intuitive Explanation of Bayes’ Theorem

by Alexandros1 min read18th Dec 20105 comments

16

Personal Blog

Common Sense Atheism has recently had a string of fantastic introductory LessWrong related material. First easing its audience into the singularity, then summarising the sequences, yesterday affirming that Death is a Problem to be Solved, and finally today by presenting An Intuitive Explanation of Eliezer Yudkowsky’s Intuitive Explanation of Bayes’ Theorem

From the article:

Eliezer’s explanation of this hugely important law of probability is probably the best one on the internet, but I fear it may still be too fast-moving for those who haven’t needed to do even algeba since high school. Eliezer calls it “excruciatingly gentle,” but he must be measuring “gentle” on a scale for people who were reading Feynman at age 9 and doing calculus at age 13 like him.

So, I decided to write an even gentler introduction to Bayes’ Theorem. One that is gentle for normal people.

It may be interesting if you want to do a review of Bayes' Theorem from a different perspective, or offer some introductory material for others. From a wider viewpoint, it's great to see a popular blog joining our cause for raising the sanity waterline.

5 comments, sorted by Highlighting new comments since Today at 5:42 AM
New Comment

Its interesting that LW was being cited as a valid authority to make deeper points like "probability is in the mind, not reality". I've never seen that tendency anywhere but here.

Anyone want to give odds on whether/when content from LW will start showing up as more authoritative than wikipedia when searching for standard terms like "cognitive bias"?

Or maybe a deeper question to motivate content generation and organization on our own part: what terms should eventually link to LW content? Any general terms like "Bayesian" or "Map vs Territory" or "Singularity"?

Type in "politics is the" and google suggests the following completions:

  • "...art of art the possible"

  • "...art of compromise"

  • "...art of art of looking for trouble"

Add an M with "politics is the m" and google changes to:

  • "...master science"

  • "...mind-killer"

  • "...master science aristotle"

  • "...management"

Just to clarify...

I didn't intend to link to LW as an authority on certain topics, but merely as a storehouse of well-written explanations for those topics.

Anyone want to give odds on whether/when content from LW will start showing up as more authoritative than wikipedia when searching for standard terms like "cognitive bias"?

How does one site show up as more authoritative than another? Isn't it simply a matter of how much trust the broader community puts into the source?

I did discover recently, to some amusement, that Harry Potter and the Methods of Rationality is the second top result for a google search on "rationality," and Eliezer's own site is the eighth.

another gentle introduction to Bayes (using R) is now available at datacamp :) https://campus.datacamp.com/courses/beginning-bayes-in-r/

This is a helpful exercise and it's always nice to have more than one wording available that tries to bridge the inferential distance.

One thing you might want to take a second look at is the first place you use the metaphor of sliding the probability - most likely you are thinking of the diagrams later in the piece, and while by the time you get to them, they're helpful, I'm not sure the description initially given is sufficient to make it more obvious what's really going on. What am I supposed to think "slide" means at this point in the piece?