The RSiena package in R is software for the analysis of network dynamcs and the co-evolution of networks and individual attributes (behavior, opinion, performance, etc.) based on longitudinal data. It implements the class of stochastic actor-oriented models, originally developed by Tom Snijders, which assumes that the social actors who are represented by the nodes in the network play a crucial role in changing their ties to other actors and their behavior. I have extended this model, which was originally formulated entirely in a Markov chain framework, with a stochastic differential equation model for the co-evolution of continuous individual attributes.
The latest version of RSiena is available on Github:
https://github.com/snlab-nl/rsiena.
You can download a tutorial on how to use the model for the
co-evolution of networks and continuous individual
attributes here (an R
Markdown file) and the corresponding data
here (an RData file). To
run this code, you will need to download the ‘nynke’ branch
of the package on GitHub (updates in this branch will be
incorporated in the main branch soon), by first installing
the remotes package in R, and then running
remotes::install_github(“snlab-nl/rsiena@nynke”)
An overview of most of the papers written on and using stochastic actor-oriented models can be found here. Refer to the following papers for more about the model for co-evolution of networks and continuous actor attributes:
The RSiena program is part of an ongoing research effort. My coding collaborators on its research team are Tom Snijders, Christian Steglich, Johan Koskinen, Viviana Amati, Christoph Stadtfeld, James Hollway, and Robert Krause. Earlier contributors are Ruth Ripley, Krists Boitmanis, Felix Schönenberger Charlotte Greenan, Josh Lospinoso, Paulina Preciado, Michael Schweinberger, Mark Huisman, and Marijtje van Duijn.
Feel free to contact me!