Mean Duration of sojourn under a treshold
Mstep.hh.MSAR.with.constraints
M step of the EM algorithm for fitting homogeneous multivariate Markov switching auto-regressive models with constraints on VAR models.
Estep of the EM algorithm for fitting (non) homogeneous Markov switching auto-regressive models.
M step of the EM algorithm for fitting homogeneous Markov switching auto-regressive models.
Plots empirical expected number of upcrossings of level u with respect to P(Y<u)
Conditional probabilities for (non) homogeneous MSAR models
fit an AR model for each class of C
Estep of the EM algorithm for fitting von Mises (non) homogeneous Markov switching auto-regressive models.
Mean Duration of sojourn over a treshold
M step of the EM algorithm for fitting von Mises Markov switching auto-regressive models.
M step of the EM algorithm.
M step of the EM algorithm for fitting homogeneous multivariate Markov switching auto-regressive models with penalization of parameters of the VAR(1) models.
M step of the EM algorithm for fitting Markov switching auto-regressive models with non homogeneous emissions.
M step of the EM algorithm for fitting homogeneous multivariate Markov switching auto-regressive models with penalization of parameters of the VAR(1) models.
M step of the EM algorithm for fitting homogeneous Markov switching auto-regressive models with constraints on the matrices.
M step of the EM algorithm for fitting homogeneous multivariate Markov switching auto-regressive models with penalization of parameters of the VAR(1) models.
M step of the EM algorithm for fitting homogeneous multivariate Markov switching auto-regressive models with SCAD penalization of parameters of the VAR(1) models.
empirical cross-correlation for multivariate MSAR time series
Winter wind data at 18 locations offshore of France
Annual GDP and Debt data 1970-2010
January wind direction at Ouessant
(Non) Homogeneous Markov switching autoregressive model
Simulation of (non) homogeneous Markov Stiwtching autoregressive models von Mises innovations
Empirical correlation functions comparison .
M step of the EM algorithm.
init.theta.MSAR (NH-MSAR)
Initialisation function for MSAR model fitting
Fit (non) homogeneous Markov switching autoregressive models
Simulation of (non) homogeneous Markov Stiwtching autoregressive models
Emission probabilities for von Mises MSAR
Plot MSAR time series with regimes
Initialisation function for von Mises MSAR model fitting
Forward Backward for MSAR models with non homogeneous transitions
M step of the EM algorithm for von Mises MSAR models
One step ahead predict for (non) homogeneous MSAR models
Statistics plotting for validation of MSAR models
Viterbi path homogeneous MSAR models
Simulates Markov chain of length T
Performs bootstrap statistical tests to validate MSAR models.
Fit von Mises (non) homogeneous Markov switching autoregressive models
Performs bootstrap statistical tests on covariance to validate MSVAR models.
Forward Backward for homogeneous MSAR models
Meteorological at Brest (France) for January month from 1973 to 2013
Forecast probabilities for (non) homogeneous MSAR models
von Mises log likelihood.