 Solution

ID: past-exam-of-the-mathematics-course-of-the-university-of-cambridge/2013/iii/paper-34/1/e/solution

Codex  0 Created 2026-10-03 Updated 2026-10-07

Use the intended hierarchical Bayesian model: the breed parameters are conditionally independent given

α, β

, and observations are independent given their breed parameters. Put

m_{i} = max (β, M_{i})

. The uniform-Pareto model evidence factorizes over breeds:

p (y_{1}, \dots, y_{I} ∣ α, β) = i = 1 \prod I \frac{α β ^{α}}{( α + n _{i} ) m _{i}^{α + n_{i}}} .

Identical marginal prior distributions alone would not determine this product; conditional independence is the additional assumption.

 New to topics? Read the docs here!