I am actively developing the R package "dtms". The package implements discrete-time multistate models in R. It comes with many tools to analyze the results of multistate models. The workflow mainly consists of estimating a discrete-time multistate model and then applying methods for absorbing Markov chains. The package comes with features for data handling and editing, several methods for estimating transition probabilities, an extensive set of Markov chain methods, and further analytical tools and methods. The most recent version of the package is available on GitHub:

https://github.com/christiandudel/dtms

I have made several methodological contributions to the literature on Markov chain methods. These contributions are described in the following papers:

Dudel, C., Schneider, D. (2023): How bad could it be? Worst-case bounds on bias in multistate models due to unobserved transitions. Sociological Methods & Research 52: 1816-1837. [Open access article] [Code]

Dudel, C. (2021): Expanding the Markov chain tool box: Distributions of occupation times and waiting times. Sociological Methods & Research 50: 401-428. [Article] [Preprint] [Code]

Dudel, C., Myrskylä, M. (2020): Estimating the number and length of episodes in disability using a Markov chain approach. Population Health Metrics 18: 15. [Open access article] [Code]

I have been teaching on multistate models for several years, both as part of the International Max Planck Research School for Population, Health and Data Science (IMPRS-PHDS) and in workshops at various institutions. If you are interested in hosting a workshop please get in touch. 

Forthcoming workshops:

Oslo Metropolitan University, January 6-7, 2026. [More information]

Hertie School, Berlin, August 17, 2026.

Previous workshops:

University of Helsinki, November 30-31, 2026.