Jeffreys prior

STA602 at Duke University

Exercise

Show that the Jeffreys prior for the normal model is \(p_J(\theta, \sigma^2) \propto (\sigma^2)^{-3/2}\).

Note: our sampling model has two unknowns. Let \(\Psi = (\theta, \sigma^2)\). Then \(p_J(\Psi) \propto \sqrt{|I(\Psi)|}\) where \(|I(\Psi)|\) is the determinant of the \(2 \times 2\) Hessian matrix.

Solution

In lab.

Exam prep

Review chapter summaries.