liveBook · Manning

Bayesian model

A Bayesian model is a probabilistic model that represents unknown quantities with prior distributions and updates them to posterior distributions using observed data and Bayes’ theorem.

How 3 Manning books explain it

Grokking Bayes

A fully Bayesian model represents uncertainty over its relevant unknown quantities with probability distributions and computes the corresponding posterior distributions.

How it is used
Uses prior knowledge and observed data to represent updated uncertainty about an unknown quantity.
How deep it goes
Works through prior–likelihood updating and normalization, then sets up a small survey example without supplying its computed posterior here.
Examples
Uses a rain prediction and a five-person tea-preference survey, contrasting uncertain inference with the point estimate 3/5.
What you can do after
Build it from scratch by assigning hypothesis priors, evaluating data likelihoods, and normalizing the resulting posterior probabilities.

Read how Grokking Bayes explains Bayesian model →

Bayesian Optimization in Action

A Bayesian model represents uncertain quantities with probability distributions and updates beliefs using observed data and Bayes' theorem.

How it is used
Updates beliefs about uncertain claims after observing data, including repeated successful predictions.
How deep it goes
Defines prior, likelihood, and posterior through a toy example while treating Bayes’ theorem only at a high level.
Examples
Uses a carnival psychic guessing secret digits one hundred times and compares three observers’ reactions.
What you can do after
Evaluate how prior beliefs influence posterior conclusions when multiple observers receive identical evidence.

Read how Bayesian Optimization in Action explains Bayesian model →

Causal AI

Bayesian modeling is the construction and analysis of probabilistic models using prior distributions, likelihoods, and posterior distributions.

How it is used
Handles uncertainty when causal assumptions and level 1 and 2 data do not identify a counterfactual query.
How deep it goes
Specifies a prior-to-posterior SCM workflow and sampling procedure, without detailing posterior computation or a general identification algorithm.
Examples
Uses a promotion-retention case involving persuadable, lost-cause, and sleeping-dog customers.
What you can do after
Evaluate/understand counterfactual uncertainty by sampling plausible SCMs after updating them with observational and interventional data.

Read how Causal AI explains Bayesian model →

Also covered in

Related concepts

Questions about Bayesian model

What is Bayesian model?

A Bayesian model is a probabilistic model that represents unknown quantities with prior distributions and updates them to posterior distributions using observed data and Bayes’ theorem.

Which Manning books explain Bayesian model?

Grokking Bayes, Bayesian Optimization in Action and Causal AI.

What are the parts of Bayesian model?

Bayesian model includes conjugacy and data.

These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.