We study the problem of modeling and inference for spatio-temporal count processes. Our approach uses parsimonious parameterisations of multivariate autoregressive count time series models, including possible regression on covariates. We control the number of parameters by specifying spatial neighbourhood structures for possibly huge matrices that take into account spatio-temporal dependencies. This work is motivated by real data applications which call for suitable models. Extensive simulation studies show that our approach yields reliable estimators.

翻译：本研究探讨了时空计数过程的建模与推断问题。我们采用多元自回归计数时间序列模型的简约参数化方法，其中包含对协变量的可能回归。通过为可能包含时空依赖性的高维矩阵指定空间邻域结构，我们有效控制了参数数量。本研究的动机源于实际数据应用中对合适模型的迫切需求。大量仿真实验表明，该方法能够产生可靠的估计量。