CITS algorithm infers causal relationships in time series data based on structural causal model and Markovian condition of arbitrary but finite order. See the paper for details.
You can get the latest version of CITS package as follows
pip install cits
- Python >= 3.6
- R >= 4.0
- R package
kpcalgand its dependencies. They can be installed in R or RStudio as follows:
> install.packages("BiocManager")
> BiocManager::install("graph")
> BiocManager::install("RBGL")
> install.packages("pcalg")
> install.packages("kpcalg")
Documentation is available at readthedocs.org
Visit this Google Colab for getting started with this package.
Alternatively, see the Getting Started in the documentation.
Your help is absolutely welcome! Please do reach out or create a future branch!
Biswas, R., Sripada, S., Mukherjee, S. & Abbasi-Asl, R. (2025) CITS: Nonparametric Statistical Causal Modeling for High-Resolution Neural Time Series. In Review. https://arxiv.org/abs/2508.01920