Stan (named after Stanislaw Ulam) is a free and open-source C++ library for probability and sampling.
Stan provides a package that will allow you to obtain Bayesian inference with the help of the No-U-Turn sampler (a variant of Hamiltonian Monte Carlo).
Stan is cross-platform and it works on Mac OS X, Windows and Linux.
Detailed instructions on how to install and use the Stan library on your Mac are available HERE.
What's New in This Release: [ read full changelog ]
Enhancements:
Modeling Language:
· forward sampling (random draws from distributions) in generated quantities
· added broadcast (repetition) functions for initializing matrices, vectors, and arrays
· better error messages in parser
additional distributions:
· exp_mod_normal
· gumbel
· skew_normal
additional functions:
· mdivide_right_spd
· mdivide_left_spd
· owenst
· columns_dot_product
· rows_dot_product
· broadcast (repetition) functions for vectors, arrays, matrices
· rep_arrray
· rep_matrix
· rep_row_vector
· rep_vector
Command-Line:
· added option to display autocorrelations in the command-line program to print output
· changed default point estimation routine from the command line to use Nesterov's accelerated gradient method, added option for point estimation with Newton's method
RStan:
· added method as.mcmc.list()
· compatibility with R 3.0.0
C++/Internal:
· refactored math/agrad libs in C++ to separate files/includes, remove redundant code, more unit tests for existing code
· added chainable_alloc ...
Find us on Google+
