= Logistic-normal regression with autoregressive random effects
A logistic-normal count model takes $Y_i\mid\theta_i\sim\operatorname{Bin}(n_i,\operatorname{logit}^{-1}\theta_i)$ and $\theta_i=x_i^T\beta+\lambda Z_i+\eta_i$, where $Z$ is a stationary unit-variance <autoregressive process of order one> with coefficient $a$ and the independent $\eta_i$ have <normal distribution> with variance $v$. The marginal latent variance is $\lambda^2+v$, and its off-diagonal <covariance> is $\lambda^2 a^{|i-j|}$. Random success probabilities produce <overdispersion> relative to the <binomial distribution>.
Back to article page
