摘要
With sparse structures and conditional independence, one could estimate the precision matrix of Gaussian graphical models more efficiently. studied objective priors for star-shape graphical models. We consider a generative star-shape model. Objective priors such as invariance priors, the Jeffreys prior and reference priors are derived for the proposed model. Closed form expressions of posterior distributions are derived based on a family of priors including the studied objective priors.