Below you'll find a section of page 110, from Gelman's 3rd edition Bayesian Data Analysis (BDA).

In the problem at hand, the observations and parameters are independent, $y_j\sim Bin(n_j,\theta_j)$, and $\theta_j\sim Beta(\alpha,\beta)$.

What's the point of trying to reparameterize first? Do they want a uniform distribution on the new parameters, and then see what they obtain for the old parametrization?

enter image description here

Any help would be appreciated.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.