liveBook · Manning

Event

As explained in Grokking Machine Learning, Second Edition

An event is an occurrence or observed outcome that provides information for updating a probability.

An event is something that occurs and provides information for updating a probability. It connects an initial probability, called the prior, to a more informed estimate, called the posterior. section 8.2

A probability update follows this simple pattern:

  • Start with the prior: an initial estimate made with little information. section 8.2
  • Observe the event: new information that changes what is known. section 8.2
  • Calculate the posterior: a revised probability that accounts for the event. section 8.2

The word “lottery” in an email

Suppose an email is spam with prior probability 0.2. Finding the word “lottery” is the event. Among 20 emails containing that word, 15 are spam, so the posterior probability is 15/20 = 0.75. section 8.5 section 8.6

Figure 8.3 The prior, the event, and the posterior. The prior is the “raw” probability, namely, the probability we calculate when we know very little. The event is the information that we obtain, which will help us refine our calculation of the probability. The posterior is the “cooked” probability, or the much more accurate probability that we calculate when we have more information.

View the prior, event, and posterior as a sequence from a raw probability to an information-refined probability. section 8.2

How Grokking Machine Learning, Second Edition covers it

How deep it goes
Defines events and works through counting, complements, conditional probabilities, and probability trees before Bayes’ theorem.
Examples
Uses rain in the Amazon rainforest, a positive medical test, and the word “lottery” in spam emails.
What it assumes
Assumes only an initial probability and builds the update from everyday information before introducing Bayes’ theorem.
What you can do after
Evaluate updated probabilities by identifying an event and comparing outcomes within the relevant subset.
How it connects
Connects events to prior probability, posterior probability, conditional probability, complementary probabilities, and Bayes’ theorem.

Also explained in

Compare how 5 books explain event →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Grokking Machine Learning, Second Edition. The section links point to the parts of the book it draws on.