panelPomp: Analysis of Panel Data via Partially Observed Markov Processes in R

TL;DR

panelPomp introduces an R package for analyzing panel data modeled as partially observed Markov processes, enabling likelihood-based inference and supporting various model manipulations for complex panel structures.

Contribution

The paper presents panelPomp, a new R package that facilitates analysis of panel data using POMP models, incorporating recent likelihood-based inference methods and flexible data manipulation tools.

Findings

Supports likelihood-based inference via simulation algorithms

Provides tools for model and data manipulation in panel structures

Enables development of new inference methodologies for panel data

Abstract

Panel data arise when time series measurements are collected from multiple, dynamically independent but structurally related systems. Each system's time series can be modeled as a partially observed Markov process (POMP), and the ensemble of these models is called a PanelPOMP. If the time series are relatively short, statistical inference for each time series must draw information from across the entire panel. The component systems in the panel are called units; model parameters may be shared between units or may be unit-specific. Differences between units may be of direct inferential interest or may be a nuisance for studying the commonalities. The R package panelPomp supports analysis of panel data via a general class of PanelPOMP models. This includes a suite of tools for manipulation of models and data that take advantage of the panel structure. The panelPomp package currently highlights recent advances enabling likelihood based inference via simulation based algorithms. However, the general framework provided by panelPomp supports development of additional, new inference methodology for panel data.