First release of mixvlmc

Mixvlmc 0.1.1 is available on the CRAN!

I am proud to announce the first release of mixvlmc, version 0.1.1. This R package provides a collection of tools to estimate and study:

• Variable Length Markov Chains (based on Bühlmann, P. and Wyner, A. J. (1999), Variable length Markov chains. Ann. Statist. 27 (2) 480-513)
• Variable Length Markov Chains with covariates (based on Zanin Zambom, A., Kim, S. and Lopes Garcia, N. (2022), Variable length Markov chain with exogenous covariates. J. Time Ser. Anal., 43 (2) 312-328)

The package comes with an extensive test suite and a complete documentation, including four vignettes on different complex aspects of these models. It includes contributions by Hugo Le Picard and Guénolé Joubioux.

Compared to VLMC and PST, mixvlmc has two major advantages:

• it includes the support of covariables;
• it supports fast BIC/AIC based automatic model selection with a post-pruning strategy.

mixvlmc is significantly faster than PST but lacks its capability of fitting a single VLMC to a collection of sequences. It also lacks some of the tools provided by PST such as its very complete set of visual representations.

mixvlmc is not as fast as VLMC but supports arbitrary large state spaces.