Hierarchical Bayesian model

A hierarchical Bayesian model assigns distributions to local latent variables conditional on shared hyperparameters, then distributions to observations conditional on those latent variables. Its probabilistic graphical model records this conditional factorization, often using a plate for repeated observations. Integrating out latent variables gives the marginal likelihood of the hyperparameters. Priors described as flat on logarithms require a Jacobian determinant when densities are written in the original positive variables.

Unknown hospital event probabilities can be modelled as exchangeable random variables conditional on shared hyperparameters, for example $P_j\mid m,\kappa \sim \mathrm{Beta}(m\kappa ,(1-m)\kappa )$ independently. Different sample sizes affect the binomial observations but do not by themselves invalidate exchangeability of the risks. Known systematic covariate differences, such as case mix or procedure type, should instead enter the risk model; only residual effects may then be exchangeable. Exchangeability permits heterogeneous realized risks and is not an assertion that all risks are equal.

// Target: biology.bigb

A normal local effect ${\alpha }_i\mid \delta ,\tau \sim N(\delta ,{\tau }^2)$ can be represented by a standardized latent variable $z_i\sim N(0,1)$ independent of the hyperparameters, with ${\alpha }_i=\delta +\tau z_i$. This preserves the hierarchical model while changing the coordinates explored by Markov chain Monte Carlo. It often improves mixing when individual effects are weakly informed, reducing strong scale-effect dependence. Centered coordinates can be better with very informative individual data. The stochastic prior on $z_i$ implements the transformation correctly; re-expressing an existing density directly instead requires the appropriate Jacobian determinant.

Partial pooling estimates related local parameters jointly through shared hyperparameters. Each local Bayesian posterior balances its own likelihood function against a group prior distribution, with stronger shrinkage when its data are weak or the group variation is small. It lies between forcing all local parameters to be equal and estimating them independently. Random-effects meta-analysis is an important application.

A Gamma–Poisson hierarchical model uses $Y_i\mid {\theta }_i\sim \mathrm{Poisson}(t_i{\theta }_i)$, ${\theta }_i\mid b\sim \mathrm{Gamma}(a,b)$, and $b\sim \mathrm{Gamma}(c,r)$, with gamma distributions in shape-rate convention. Conditional independence gives full conditional distributions ${\theta }_i\mid b,y\sim \mathrm{Gamma}(a+y_i,b+t_i)$ and $b\mid \theta ,y\sim \mathrm{Gamma}(c+na,r+{\sum }_i{\theta }_i)$.

For $Y_i\mid {\theta }_i\sim \mathrm{Poisson}({\theta }_i)$ and ${\theta }_i\mid \psi \sim \mathrm{Exp}(\psi )$, a scale-invariant prior $d\psi /\psi$ induces the Haldane prior on $\varphi =(1+\psi {)}^{-1}$. Integrating out each local mean gives $p(y_i\mid \varphi )=(1-\varphi ){\varphi }^{y_i}$. Thus $\varphi \mid y\sim \mathrm{Beta}(s,n)$ for $s={\sum }_i{y}_i>0$. The gamma full conditional distribution has mean $(y_i+1)\varphi$, so the tower property gives $(y_i+1)s/(s+n)$, equal to the displayed partial pooling formula. For $s=0$, the posterior is improper and this expectation is undefined.

For independent Poisson distributions with means $u{e}^{{\eta }_k}$ and a shape–rate Gamma distribution prior on $u$, integrating $u$ adds $a$ to the total-count exponent and $b$ to the sum of relative rates. This distinguishes gamma mixing from conditioning on the total count, which gives a multinomial distribution.

An observed astronomical colour is the sum of a normal intrinsic colour, a nonnegative dust contribution with an exponential distribution, and normal measurement noise. With latent $C_s\sim N(\mu ,v)$, $E_s\sim \mathrm{Exp}(\text{mean }\tau )$ and $O_s\mid C_s,E_s\sim N(C_s+E_s,r_s)$, the Gibbs sampler conditionals for $C_s$ are normal and those for $E_s$ are truncated normal distributions. A flat prior on $\mu$ and inverse-gamma priors on $v,\tau$ give inverse-gamma conditional updates for the two scales. Log-flat priors on both scales instead make the joint posterior improper when all $r_s>0$, despite formally proper full conditionals at generic latent states: the marginal observed likelihood has a positive limit at either zero-scale boundary. Proper positive-scale priors restore a genuine joint posterior.