PNAR: Poisson Network Autoregressive Models

Quasi likelihood-based methods for estimating Poisson Network Autoregression with p lags, PNAR, following generalized linear models are provided. PNAR models with the identity and with the logarithmic link function are allowed. The inclusion of exogenous covariates is also possible. Moreover, it provides tools for testing the linearity of linear PNAR model versus several nonlinear alternatives. Finally, it allows generating multivariate count distributions, from linear and nonlinear PNAR models, where the dependence between Poisson random variables is generated by suitable copulas. References include: Armillotta, M. and K. Fokianos (2022a). Poisson network autoregression. <arXiv:2104.06296>. Armillotta, M. and K. Fokianos (2022b). Testing linearity for network autoregressive models. <arXiv:2202.03852>.

Version: 1.0
Depends: R (≥ 4.0)
Imports: doParallel, foreach, igraph, nloptr, parallel, Rfast, Rfast2, stats
Published: 2022-06-08
Author: Michail Tsagris [aut, cre], Mirko Armillotta [aut, cph], Konstantinos Fokianos [aut]
Maintainer: Michail Tsagris <mtsagris at>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: no
CRAN checks: PNAR results


Reference manual: PNAR.pdf


Package source: PNAR_1.0.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): PNAR_1.0.tgz, r-oldrel (arm64): PNAR_1.0.tgz, r-release (x86_64): PNAR_1.0.tgz, r-oldrel (x86_64): PNAR_1.0.tgz


Please use the canonical form to link to this page.