stmar_to_gstmar estimates a G-StMAR model based on StMAR model with large degree
of freedom parameters
stmar_to_gstmar(gsmar, maxdf = 100, estimate, calc_std_errors,
maxit = 100, custom_h = NULL)object of class 'gsmar' created with the function fitGSMAR or GSMAR.
regimes with degrees of freedom parameter value large than this will be turned into GMAR type.
set TRUE if the new model should be estimated with variable metric algorithm using the StMAR model
parameters as the initial values. By default TRUE iff the model contains data.
set TRUE if the approximate standard errors should be calculated.
By default TRUE iff the model contains data.
the maximum number of iterations for the variable metric algorithm. Ignored if estimate==FALSE.
A numeric vector of with same length as the parameter vector of the estimated model: i:th element
of custom_h is the difference used in central difference approximation for differentials of the log-likelihood function
for the i:th parameter. If NULL (default), then the difference used for differentiating overly large degrees of
freedom parameters is adjusted to avoid numerical problems, and the difference is 6e-6 for the other parameters.
Returns an object of class 'gsmar' defining the specified GMAR, StMAR or G-StMAR model. If data is supplied, the returned object
contains (by default) empirical mixing weights, conditional means and variances and quantile residuals. Note that the first p observations are
taken as the initial values so mixing weights, conditional moments and qresiduals start from the p+1:th observation (interpreted as t=1).
If a StMAR model contains large estimates for the degrees of freedom parameters
one should consider switching to the corresponding G-StMAR model that lets the corresponding regimes to be GMAR type.
stmar_to_gstmar makes it convenient to do this switch.
Kalliovirta L., Meitz M. and Saikkonen P. 2015. Gaussian Mixture Autoregressive model for univariate time series. Journal of Time Series Analysis, 36, 247-266.
Meitz M., Preve D., Saikkonen P. 2018. A mixture autoregressive model based on Student's t-distribution. arXiv:1805.04010 [econ.EM].
There are currently no published references for the G-StMAR model, but it's a straightforward generalization with theoretical properties similar to the GMAR and StMAR models.
fitGSMAR, GSMAR, iterate_more, get_gradient,
get_regime_means, swap_parametrization, stmar_to_gstmar
# NOT RUN {
# These are long running examples and use parallel computing
fit13tr <- fitGSMAR(logVIX, 1, 3, model="StMAR", restricted=TRUE,
ncalls=1, seeds=1)
fit13tr
fit13gsr <- stmar_to_gstmar(fit13tr)
fit13gsr
# }
Run the code above in your browser using DataLab