Bassist is a tool that automates the use of hierarchical Bayesian models in complex analysis tasks. Such models offer a powerful framework for modeling statistically complex real-world phenomena. So far, the lack of computational tools has hindered the practical use of hierarchical Bayesian models.
Bayesian models are specified to Bassist in terms of its high-level language. Given a model specification, Bassist generates a model-specific program for the analysis of data files. The generated program applies MCMC (Markov chain Monte Carlo) approximation, in particular the Metropolis-Hastings method, to obtain a sample from the posterior distribution of the parameters and missing data.
Bassist has been developed at the Department of Computer Science of University of Helsinki.
Bassist is not actively developed and maintained anymore. Some problems in compiling the source code with newer versions of compilers are anticipated. Unfortunately we don't have the resources to actively support users. (In an absolute emergency, you can direct technical questions to Jouni Seppänen.)