Poisson Network Autoregression

04/13/2021

∙

by   Mirko Armillotta, et al.

∙

0

∙

share

We consider network autoregressive models for count data with a non-random time-varying neighborhood structure. The main methodological contribution is the development of conditions that guarantee stability and valid statistical inference. We consider both cases of fixed and increasing network dimension and we show that quasi-likelihood inference provides consistent and asymptotically normally distributed estimators. The work is complemented by simulation results and a data example.