M step of the EM algorithm for fitting von Mises Markov switching auto-regressive models.

Description

M step of the EM algorithm for fitting homogeneous Markov switching auto-regressive models, called in fit.MSAR.VM.

Usage

1
Mstep.hh.MSAR.VM(data, theta, FB, constr = 0)

Arguments

data

array of univariate or multivariate series with dimension T*N.samples*d. T: number of time steps of each sample, N.samples: number of realisations of the same stationary process, d: dimension.

theta

model's parameter; object of class MSAR. See also init.theta.MSAR.

FB

Forward-Backward results, obtained by calling Estep.MSAR function

constr

constraints are added to the κ parameter (A preciser)

Details

The homogeneous MSAR model is labeled "HH" and it is written

P(X_t|X_{t-1}=x_{t-1}) = Q_{x_{t-1},x_t}

with X_t the hidden univariate process defined on \{1,\cdots,M \}

Y_t|X_t=x_t,y_{t-1},...,y_{t-p}

has a von Mises distribution with density

p_2(y_t|x_t,y_{t-s}^{t-1}) = \frac {1}{b(x_t,y_{t-s}^{t-1})} \exp≤ft(κ_0^{(x_t)} \cos(y_t-φ_0^{(x_t)})+ ∑_{\ell=1}^sκ_\ell^{(x_t)} \cos(y_t-y_{t-\ell}-φ_\ell^{(x)})\right)

which is equivalent to

p_2(y_t|x_t,y_{t-s}^{t-1}) = \frac {1}{b(x_t,y_{t-s}^{t-1})} ≤ft|\exp≤ft([γ_0^{(x_t)} + ∑_{\ell=1}^sγ_\ell^{(x_t)} e^{iy_{t-\ell}}]e^{-iy_t}\right)\right|

b(x_t,y_{t-s}^{t-1}) is a normalisation constant.

Both the real and the complex formulation are implemented. In practice, the complex version is used if the initial κ is complex.

Value

List containing

mu

intercepts

kappa

von Mises AR coefficients

prior

prior probabilities

transmat

transition matrix

Author(s)

Valerie Monbet, valerie.monbet@univ-rennes1.fr

References

Ailliot P., Bessac J., Monbet V., Pene F., (2014) Non-homogeneous hidden Markov-switching models for wind time series. JSPI.

See Also

fit.MSAR.VM, Estep.MSAR.VM

Want to suggest features or report bugs for rdrr.io? Use the GitHub issue tracker.