The pizza place example that was introduced in the chapter, and in Figure 11-9, suggests an interaction between the strength of our prior beliefs and the amount of data that we have in determining how much we change our beliefs—that is, how different the posterior distribution is from the prior. What is this relation and what does it suggest about how sample size plays a role in Bayesian belief updating?

Figure 11-9

Transcribed Image Text:

(a) Degree of belief Posterior Prior 50 100% Likelihood pizza place is open (b) Degree of belief Posterior Prior 50 100% Likelihood pizza place is open (c) Degree of belief Posterior Prior 50 100% Likelihood pizza place is open