GDAGsim: Sparse matrix algorithms for Bayesiancomputation

摘要

GDAGsim is a software library which can be used to carry out conditional samplingrnof linear Gaussian directed acyclic graph models, and hence can be used for the implementationrnof efficient block MCMC samplers for such models. This paper examinesrnthe software library and its design, and how it can be applied to problems in Bayesianrninference.