Further clarifications about oblig + Drop-in session on Tuesday
Based on some questions I have received, I want to clarify two things in the oblig:
Problem 1b: If we want to pay full attention to what is conditioned on at each step, the setup is as follows:
- θ ~ π( . ) (prior)
- y | θ ~ π( . | θ) (forward/observation model)
- θ' | y ~ π( . | y) (posterior)
The question then asks for the marginal distribution of θ'.
Problem 3
I write that Xn+1~ Uniform{x1, ..., xn}, but this notation is misleading, since we do not want to think of {x1, ..., xn} as a set here. Instead, like equation (2) indicates, what I mean is that Xn+1 takes the value x1 with probability 1/n, x2 with probability 1/n, ..., xn with probability 1/n. A better notation would be Xn+1~ Uniform(x1, ..., xn).
Drop-in session on Tuesday
Since you are all busy with the oblig, and I do not want to rush through more lecture material before we have to, we will have a drop-in session on Tuesday (same room, same place), where you can show up and ask questions. I will prioritise questions about the oblig, but I am happy to take questions on other bits of the syllabus if time allows.