Statistical Inference for Spatiotemporal Partially Observed Markov Processes via the R Package spatPomp
Statistical Inference for Spatiotemporal Partially Observed Markov Processes via the R Package spatPomp
复制标题
通过 R 包 spatPomp 对时空部分观测马尔可夫过程进行统计推断
DOI:
--
复制
发表时间:
2021
期刊:
影响因子:
--
通讯作者:
E. Ionides
中科院分区:
文献类型:
--
作者:
Kidus Asfaw;Joonha Park;Allister Ho;A. King;E. Ionides
We consider inference for a class of nonlinear stochastic processes with latent dynamic variables and spatial structure. The spatial structure takes the form of a finite collection of spatial units that are dynamically coupled. We assume that the latent processes have a Markovian structure and that unit-specific noisy measurements are made. A model of this form is called a spatiotemporal partially observed Markov process (SpatPOMP). The R package spatPomp provides an environment for implementing SpatPOMP models, analyzing data, and developing new inference approaches. We describe the spatPomp implementations of some methods with scaling properties suited to SpatPOMP models. We demonstrate the package on a simple Gaussian system and on a nontrivial epidemiological model for measles transmission within and between cities. We show how to construct user-specified SpatPOMP models within spatPomp . This document is provided under the Creative Commons Attribution License.
影响因子:
3.4
作者:
Brown GD;Porter AT;Oleson JJ;Hinman JA
通讯作者:
Hinman JA
DOI:
10.1080/01621459.2019.1592753
发表时间:
2017-04
影响因子:
3.7
作者:
M. Katzfuss;Jonathan R. Stroud;C. Wikle
通讯作者:
M. Katzfuss;Jonathan R. Stroud;C. Wikle
影响因子:
2.2
作者:
通讯作者:
--