Notes
Ch 1: Introduction

Bayes Theorem
1.2: Bayes Theorem
Example 1.2
 A: disease presence

B: result test
 95% effective when disease present
 1% false positive

0.5% of population has disease

(a) Calculate the probability that a person who tests positive actually has the disease.
There is a 32.3% chance that a person who tests positive actually has the disease.

(b) Find the probability that a person who tests negative does not have the disease.
There is a 99.97% chance that a person who tests negative does not have the disease.
1.3: Likelihood
 Suppose that an experiment results in data x = (x1, x2, … , xn) T and we decide to model the data using a probability (density) function f(xθ). This p(d)f describes how likely different data x are to occur given a value of the (unknown) parameter θ. However, once we have observed the data, f(xθ) tells us how likely different values of the parameters θ are: it is then known as the likelihood function for θ. In other courses you may have seen it written as L(θx) or L(θ) but, whatever the notation used for the likelihood function, it is simply the joint probability (density) function of the data, f(xθ), regarded as a function of θ rather than of x.
Example 1.5
The likelihood function for follows the formulation in the section introduction.