Bayesian Methods for State Space Models
Auxiliary Particle Filter (APF)
bayesSSM: Bayesian Inference for State-Space Models
Bootstrap Particle Filter (BPF)
Create Tuning Control Parameters
Internal function to back-transform parameters
Helper function to validate input of user-defined functions and priors
Internal function to compute the Jacobian of the transformation
Ensure that a function has a ... argument
Core Particle Filter Function
Pilot Run for Particle Filter Tuning
Run Pilot Chain for Posterior Estimation
Internal function to transform parameters
Estimate effective sample size (ESS) of MCMC chains.
Common Parameters for Particle Filters
Model Specification for Particle Filters
Shared Return Values for Particle Filters
Particle filter functions
Particle Marginal Metropolis-Hastings (PMMH) for State-Space Models
Print method for PMMH output
Resample-Move Particle Filter (RMPF)
Compute split Rhat statistic
Summary method for PMMH output
Implements methods for Bayesian analysis of State Space Models. Includes implementations of the Particle Marginal Metropolis-Hastings algorithm described in Andrieu et al. (2010) <doi:10.1111/j.1467-9868.2009.00736.x> and automatic tuning inspired by Pitt et al. (2012) <doi:10.1016/j.jeconom.2012.06.004> and J. Dahlin and T. B. Schön (2019) <doi:10.18637/jss.v088.c02>.
Useful links