From: Hierarchical Bayesian adaptive lasso methods on exponential random graph models
Variable | Proportional Distribution |
---|---|
\(\displaystyle \frac{1}{\tau _{j}}\) | \(\text {Inverse Gaussian} \left( \sqrt{\frac{\lambda _{j}^{2} \sigma ^{2}}{\theta _{j}^{2}} }, \lambda _{j}^{2} \right)\) |
\(\lambda _{j}^{2}\) | \(\text {Gamma} \left( 2, \frac{\tau _{j}^{2}}{2} \right)\) |
\(\sigma ^{2}\) | \(\text {Inverse Gamma} \left( \frac{p}{2} , \frac{1}{2} \varvec{\theta }^{T} D_{\varvec{\tau }}^{-1} \varvec{\theta } \right)\) |