runMCMC: Run MCMC iterations

In TheoMichelot/MScrawl: Multistate Continous-Time Correlated Random Walks

Description

Run MCMC iterations

Usage

runMCMC(track, nbStates, nbIter, inits, priors, props, tunes, kalmanpars,
  updateState = TRUE)

Arguments

track	Dataframe of data, with columns "x", "y", and "time"
nbStates	Number of states
nbIter	Number of iterations
inits	List of initial parameters (beta, sigma, Q, state)
priors	List of parameters of prior distributions, with components: "mean": Vector of means for normal priors on movement parameters, of length 2*nbStates "sd": Vector of standard deviations for normal priors on movement parameters, of length 2*nbStates "shape": Vector of shapes of gamma priors for the transition rates "rate": Vector of rates of gamma priors for the transition rates "con": Vector of concentrations of Dirichlet priors for transition probabilities
props	List of parameters of proposal distributions, with components: "betaSD": Scalar standard deviation for normal proposal distribution of beta "sigmaSD": Scalar standard deviation for normal proposal distribution of sigma "updateLim": Vector of two values: min and max length of updated state sequence "updateProbs": Probability for each element of updateLim[1]:updateLim[2] (if NULL, all values are equiprobable)
tunes	List of tuning parameters, with components: "thinStates": Thinning factor for the posterior state sequences (needed because of memory limitations)
kalmanpars	List of parameters of the Kalman filter, with components: "Hmat": Matrix of observation error variance (four columns, and one row for each row of data) "a0": Initial state estimate vector "P0": Initial estimate covariance matrix
updateState	Logical. If FALSE, the state process is not updated (for exploratory analysis only)

TheoMichelot/MScrawl documentation built on Dec. 10, 2019, 10:44 a.m.