Event

As explained in Grokking Machine Learning

In Bayesian reasoning, an event is an occurrence or observation that provides information for updating a probability.

An event is information—something observed or discovered—that helps update a probability. Start with a prior, the estimate based on little information; use the event to calculate a posterior, a revised estimate. section 8.1

A word in an email

Suppose 20 emails contain “lottery”: 15 are spam and 5 are not. Finding that an email contains the word is the event; among those emails, the estimated probability of spam is 15/20, or 0.75. section 8.2

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.

The diagram connects the prior, event, and posterior as successive parts of an updated probability estimate. section 8.1

How Grokking Machine Learning covers it

How deep it goes

Defines events and illustrates their effect with medical and email examples before introducing Bayes’ theorem.

Examples

Uses a positive medical diagnosis, the Amazon rain forest, and the word “lottery” in spam emails.

What you can do after

Apply Bayesian reasoning to update a probability using an informative observation.

How it connects

Connects events to prior probability, posterior probability, Bayes’ theorem, and naive Bayes.

liveBookmanning.com

Read Grokking Machine Learning on liveBook Get the book at manning.com

Related concepts

• posterior probabilityused by · A posterior probability or distribution expresses the probability assigned to an event, hypothesis, or unknown quantity conditional on observed evidence and prior information.
• bayesian statisticsused by · Bayesian statistics is a framework for statistical inference that combines prior probability distributions with observed-data likelihoods to update probabilities over hypotheses or unknown quantities.
• naive bayes classifierused by · A Naive Bayes classifier is a probabilistic classification model that applies Bayes’ theorem while assuming features are conditionally independent given the class.
• mutually exclusive eventaddressed by · Mutually exclusive events are events that cannot occur simultaneously and have no outcomes in common.
• complementincludes · The complement of a set or event is the subset of a specified universe containing all elements or outcomes not in that set or event.
• probability theoryused by · Probability theory is the branch of mathematics that formalizes uncertainty and analyzes random events and outcomes using probability measures.

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