Inference for Spatiotemporal Partially Observed Markov Processes
Adapted Bagged Filter (ABF)
Adapted Bagged Filter with Intermediate Resampling (ABF-IR)
Calculated log-ARMA log-likelihood benchmark for spatPomp models
Coerce to data frame
Exact log-likelihood for Brownian motion spatPomp generator
Brownian motion spatPomp simulator
Exact log-likelihood for Brownian motion spatPomp generator with share...
Brownian motion spatPomp generator with shared or unit-specific parame...
Block particle filter (BPF)
Concatenate spatPomp objects into a listie
Concatenate
dunit_measure dunit_measure evaluates the unit measurement density o...
Generalized Ensemble Kalman filter (EnKF)
Expectation of the measurement model for one unit
Geometric Brownian motion spatPomp simulator
Guided intermediate resampling filter (GIRF)
Measles in UK: spatPomp generator with shared or unit-specific paramet...
Iterated block particle filter (IBPF)
Iterated ensemble Kalman filter (IEnKF)
Iterated guided intermediate resampling filter (IGIRF)
Iterated Unadapted Bagged Filter (IUBF)
listie: List-like objects
Log likelihood extractor
Lorenz '96 spatPomp constructor
Measles in UK spatPomp generator
Measles in UK: spatPomp generator with shared or unit-specific paramet...
Matching moments for the unit measurement model
Book-keeping functions for working with expanded parameters
Plot methods for spatPomp objects
Print methods
pStop
Random draw from the measurement model for one unit
Simulation of a spatiotemporal partially-observed Markov process
C snippets
An S4 class to represent a spatiotemporal POMP model and data.
Inference for SpatPOMPs (Spatiotemporal Partially Observed Markov Proc...
Constructor of the spatPomp object
Undefined
Unit names of a spatiotemporal model
Vector of unit measurement densities for each unit
Vector simulating measurements for each unit using runit_measure
Conditional variance of the measurement on a single unit
Inference on panel data using spatiotemporal partially-observed Markov process (SpatPOMP) models. The 'spatPomp' package extends 'pomp' to include algorithms taking advantage of the spatial structure in order to assist with handling high dimensional processes. See Asfaw et al. (2024) <doi:10.48550/arXiv.2101.01157> for further description of the package.
Useful links