nuisanceModel_mean: Normal mean model, with nuisance time series

Description

This class represents the mean model X_t=mu+e_t with mu~N(mu.mu0,mu.sd^2) and e_t being a nuisance parameter time series

Usage

nuisanceModel_mean(mu.mu0 = 0, mu.sd = 10000, prop.scaling = 1)

Arguments

mu.mu0, mu.sd

A priori mean and standard deviation of mu

prop.scaling

Scaling parameter for generating Metropolis-Hastings proposals of parameter of interest theta=mu

Value

S3 nuisanceModel object representing the model parameter theta=mu of interest, containing the following fields:

theta_dim

Dimension of parameter of interest (here: theta_dim=1)

excludeBoundary

Logical; Should the outermost Fourier frequencies be ignored in the frequency domain representation? (here: excludeBoundary=F)

get_noise

Function taking the two arguments data,theta to compute the nuisance/noise time series e_t from data and parameter theta of interest. (here: e_t=data-theta)

propose_next_theta

Function taking the parameters data (Numeric vector of input data), f (Numeric Vector of current spectral density at the Fourier frequencies within the Gibbs sampling algorithm) and previous_theta (Previously sampled value of mu) and returning a new proposal value for mu

initialize_theta

Function taking the Numeric Vector data of input data as argument to generate an initial value for mu to start an MCMC algorithm (here: mean(data))

lprior_theta

Function; Log density of prior of mu (here: log density of N(mu.mu0,mu.sd^2))

Details

The returned object of this function is intended for usage within gibbs_AR_nuisance, gibbs_NP_nuisance and gibbs_NPC_nuisance. The method propose_next_theta is optimized to be close to the marginal posterior of mu in the model. The proposal scaling can be controlled with the parameter prop.scaling, where larger values yield a broader (smaller values yield narrower) proposal distribution.