liveBook · Manning

Theoretical probability

As explained in Statistics Every Programmer Needs

Theoretical probability is the ratio of the number of favorable outcomes to the total number of possible outcomes in a specified probability model.

Theoretical probability computes an event’s chance from a specified model rather than from observations. It divides favorable outcomes by total possible outcomes, assuming a fixed setting with equally likely outcomes. section 2.1 section 2.5

Use the model and event structure to choose the appropriate calculation.

  • Count favorable outcomes and divide by all possible outcomes. section 3.2
  • Apply the multiplication rule to independent events occurring together or in sequence. section 2.5 section 3.2
  • Apply the addition rule to mutually exclusive events that cannot occur simultaneously. section 2.5 section 3.2
  • Distinguish theoretical probability from empirical probability, which uses observed successes divided by observations. section 2.5

Rolling a six-sided die

For an even result, three of six outcomes are favorable, so the theoretical probability is 3/6, or 50%. For a 4, it is 1/6, approximately 16.7%; the corresponding odds are 1/5, or 20%. section 3.2

How Statistics Every Programmer Needs covers it

How deep it goes
Defines the favorable-outcome ratio and connects it to counting rules, but stops short of formal proofs or computational implementation.
Examples
Uses coin flips, repeated card selection, single-die events, paired dice, and cumulative probabilities for discrete outcomes.
What it assumes
Assumes only identifiable outcomes and events, while developing favorable-outcome counting, independence, mutual exclusivity, and replacement distinctions.
What you can do after
Evaluate/understand event chances, combine independent or mutually exclusive events, and distinguish model-based probabilities from observed rates.
How it connects
Connects theoretical probability with empirical probability, the law of large numbers, multiplication and addition rules, counting, and cumulative distribution functions.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Statistics Every Programmer Needs. The section links point to the parts of the book it draws on.