Statistical Inference for Partially Observed Markov Processes via theRPackagepomp

Abstract

Partially observed Markov process (POMP) models, also known as hidden Markov models or state space models, are ubiquitous tools for time series analysis. The R package pomp provides a very flexible framework for Monte Carlo statistical investigations using nonlinear, non-Gaussian POMP models. A range of modern statistical methods for POMP models have been implemented in this framework including sequential Monte Carlo, iterated filtering, particle Markov chain Monte Carlo, approximate Bayesian computation, maximum synthetic likelihood estimation, nonlinear forecasting, and trajectory matching. In this paper, we demonstrate the application of these methodologies using some simple toy problems. We also illustrate the specification of more complex POMP models, using a nonlinear epidemiological model with a discrete population, seasonality, and extra-demographic stochasticity. We discuss the specification of user-defined models and the development of additional methods within the programming environment provided by pomp. *This document is a version of a manuscript in press at the Journal of Statistical Software. It is provided under the Creative Commons Attribution License. Partially observed Markov processesapproximations are adequate for one's purposes, or when the latent process takes values in a small, discrete set, methods that exploit these additional assumptions to advantage, such as the extended and ensemble Kalman filter methods or exact hidden-Markov-model methods, are available, but not yet as part of pomp. It is the class of nonlinear, non-Gaussian POMP models with large state spaces upon which pomp is focused.A POMP model may be characterized by the transition density for the Markov process and the measurement density 1 . However, some methods require only simulation from the transition density whereas others require evaluation of this density. Still other methods may not work with the model itself but with an approximation, such as a linearization. Algorithms for which the dynamic model is specified only via a simulator are said to be plug-and-play (Bretó et al. 2009;He et al. 2010). Plug-and-play methods can be employed once one has "plugged" a model simulator into the inference machinery. Since many POMP models of scientific interest are relatively easy to simulate, the plug-and-play property facilitates data analysis. Even if one candidate model has tractable transition probabilities, a scientist will frequently wish to consider alternative models for which these probabilities are intractable. In a plug-andplay methodological environment, analysis of variations in the model can often be achieved by changing a few lines of the model simulator codes. The price one pays for the flexibility of plugand-play methodology is primarily additional computational effort, which can be substantial. Nevertheless, plug-and-play methods implemented using pomp have proved capable for state of the art inference problems (e.g., King et al. 2008;Bhadra et al. 2011;Shrestha et al. 2011Shrestha et al. , 2013Earn et al. 2012...

Differential and enhanced response to climate forcing in diarrheal disease due to rotavirus across a megacity of the developing world

“…The estimation of both parameters and initial conditions for all state variables was carried out with an iterated filtering algorithm (MIF, for maximum likelihood iterated filtering) implemented in the R package "pomp" [partially observed Markov processes (43)(44)(45)]. This algorithm maximizes the likelihood and allows for the inclusion of both measurement and process noise, in addition to hidden variables, which is a typical limitation of surveillance records that provide a time series for a single observed variable per region.…”

Digital epidemiology reveals global childhood disease seasonality and the effects of immunization

“…the process noise dispersion parameter (θ), and the reporting dispersion parameter (τ) of a normal distribution, with a mean of 1, from which case reports were drawn. The parameters were estimated using maximum likelihood by iterated particle filtering in the R-package pomp (40,41). The Google Trends model fit the case data (SI Appendix, Fig.…”

Continuous Time Structural Equation Modeling with R Package ctsem

“…These include sde (Iacus 2016), yuima (Brouste et al 2014), SIM.DiffProc (Guidoum and Boukhetala 2017), cts (Wang 2013), POMP (King, Nguyen, and Ionides 2016). For multisubject approaches, OpenMx (Neale et al 2016) now includes the function mxExpectationStateSpaceContinuousTime, which can be combined with the function mxFitFunctionMultigroup for fixed effects based group analysis.…”