This work is licensed under a Creative Commons Attribution 4.0 International License.
PyMsBayes has only been tested on version 2.7 of Python. The only Python dependency is ConfigObj. This dependency should get installed automatically when you follow the instructions for installing PyMsBayes in the “Installation” section. However, if it does not, it can easily be installed using pip install configobj or easy_install configobj; see http://www.voidspace.org.uk/python/configobj.html#installing for more details.
If you wish to use any of the plotting features of PyMsBayes, you will need to install matplotlib.
For post-hoc regression adjustment of posterior samples, the general linear model (GLM) method of Leuenberger and Wegmann [7] is the default, and does not require any extra dependencies. However, if you wish to use the weighted local-linear regression (multinomial logistic regression for discrete parameters) method of Beaumont et al. [1] via the API, then you will need to install the following R packages: VGAM, KernSmooth, locfit, and optparse.