Chapter 4: Probability: To Bayes or Not To Bayes?
—
Today's Amazon Deals - https://amzn.to/3FeoGyg)
—-
Chapter 4: Probability: To Bayes or Not To Bayes?
Overview
“Life is a school of probability.”
—William Bagehot
What is probability?
If you’re not a data scientist, you likely have an intuitive understanding of probability from school lessons or based on common sense. For many events, it is impossible to always correctly predict the outcome in advance. But we know that some outcomes are more likely than others. Put simply, probability is a way to express and study which outcomes are more, or less, likely to happen. The etymology of the word “probable” has an interesting bearing on how we use it today; it comes from the 14th century French word probable, meaning “provable or demonstrable,” originally derived from the Latin verb probare—“to try, to test.”
If I asked you what’s the probability of getting tails on a coin flip on a fair coin, you would probably say 50 percent. Intuitively it makes sense. However, you might not be able to explain why this should be true mathematically. Coin-flipping is a simple case for calculating probabilities. How would you define the probability of Manchester United winning the next Champions League? You might have your own personal beliefs about which football team is the best (and this belief could change every year), but the way you come up with this probability “feels” different from the coin-flipping case.
