Reverse a conditional probability and update it on evidence. Start with Bayes' theorem and its prior, likelihood and posterior, then build its denominator with the law of total probability and see why a rare condition gives mostly false positives. Finish with odds, the odds form of Bayes' rule and the log-odds scale, and combine several pieces of evidence.
No account needed to read a lesson · 30-day money-back guarantee
See the full learning path4
lessons
41
practice questions
63
prerequisite lessons
1 of the 4 lessons here is free to preview - the whole explanation and worked example, with no account and no email.
Live, not a screenshot
Lesson 01 · Bayes' theorem
Each region of
Both conditional probabilities use the same overlap, the
The diagram from the lesson itself, running live.
4 lessons you can take today, and 3 more being written. Expand any one to see what it covers. Each unlocks when its own prerequisites are passed.
01
Bayes' theorem
12 questions
Learn which of two conditional probabilities is larger, how Bayes' rule finds a conditional probability from the reverse one, and what the prior, likelihood and posterior are.
Covers
Which is larger, or ?
Bayes' rule
Prior, likelihood and posterior
02
Bayes with total probability
8 questions
Learn how to apply Bayes' rule when its denominator is not given, finding it with the law of total probability over a partition.
Covers
Two groups
A partition
03
Odds
9 questions
Learn how to turn a probability into odds, read odds written as "a to b", find the odds that an event does not happen, and convert odds back into a probability.
Covers
Odds from a probability
Probability from odds
04
The log-odds scale
12 questions
Learn how to find the log-odds of an event from its odds, what the sign and size of a log-odds value say about how likely the event is, and how to turn log-odds back into a probability.
Covers
Log-odds of an event
Properties of log-odds
Probability from log-odds
—
Base rates and test results
In drafting
—
The odds form of Bayes' rule
In drafting
—
Combining evidence
In drafting
This unit is part of our Essential Probability & Statistics for ML learning path, which contains 80 lessons. Every one of them is drawn below.
The diagnostic test lets you skip any lesson you already know, including the ones in this unit.
Hover any dot to name its lesson.
4 lessons in this unit
63 prerequisite lessons across the unit, counting every step back to the start
13 other lessons in the learning path - after this unit, or alongside it
One subscription covers every learning path, and you can test out of anything you already know.
One subscription covers every learning path · 30-day money-back guarantee
More in Probability and Statistics: Sample spaces and events, Counting, Probability fundamentals, Conditional probability and independence