This function is a wrapper that applies mtar() over a grid of model specifications
defined by all combinations of the noise distribution (dist), the number of regimes
(from nregim.min to nregim.max), the autoregressive order within each regime
(from p.min to p.max), the maximum lag of the exogenous series within each regime
(from q.min to q.max), and the maximum lag of the threshold series within each
regime (from d.min to d.max).
In all calls to mtar(), the same set of time points is used for model fitting. This is
achieved by appropriately adjusting the subset argument of mtar() for each model
specification, thereby ensuring comparability across models.
mtar_grid(
formula,
data,
subset,
Intercept = TRUE,
trend = c("none", "linear", "quadratic"),
nseason = NULL,
nregim.min = 1,
nregim.max = NULL,
p.min = 1,
p.max = NULL,
q.min = 0,
q.max = 0,
d.min = 0,
d.max = 0,
row.names,
dist = "Gaussian",
prior = list(),
n.sim = 500,
n.burnin = 100,
n.thin = 1,
ssvs = FALSE,
setar = NULL,
plan_strategy = c("sequential", "multisession"),
progress = TRUE
)A list whose elements are objects of class mtar, each corresponding to a distinct
model specification considered in the grid.
A three-part expression of class Formula describing the TAR model to be fitted.
The first part specifies the variables in the multivariate output series, the second part
defines the threshold series, and the third part specifies the variables in the multivariate
exogenous series.
A data frame containing the variables in the model. If not found in data, the
variables are taken from environment(formula), typically the environment from
which mtar_grid() is called.
An optional vector specifying a subset of observations to be used in the fitting process.
An optional logical indicating whether an intercept should be included within each regime.
An optional character string specifying the degree of deterministic time trend to be
included in each regime. Available options are "linear", "quadratic", and
"none". By default, trend is set to "none".
An optional integer, greater than or equal to 2, specifying the number of seasonal periods.
When provided, nseason - 1 seasonal dummy variables are added to the regressors within each regime.
By default, nseason is set to NULL, thereby indicating that the TAR model has no seasonal effects.
An optional integer specifying the minimum number of regimes. By default,
nregim.min is set to 1.
An integer specifying the maximum number of regimes.
An optional integer specifying the minimum autoregressive order within each regime.
By default, p.min is set to 1.
An integer specifying the maximum autoregressive order within each regime.
An optional integer specifying the minimum value of the maximum lag of the exogenous
series within each regime. By default, q.min is set to 0.
An optional integer specifying the maximum value of the maximum lag of the exogenous
series within each regime. By default, q.max is set to 0.
An optional integer specifying the minimum value of the maximum lag of the threshold
series within each regime. By default, d.min is set to 0.
An optional integer specifying the maximum value of the maximum lag of the threshold
series within each regime. By default, d.max is set to 0.
An optional variable in data labelling the time points corresponding to each row of the data set.
A character vector specifying the multivariate distributions used to model the noise
process. Available options are "Gaussian", "Student-t", "Slash",
"Hyperbolic", "Laplace", "Contaminated normal",
"Skew-normal", and "Skew-Student-t". By default, dist is set to
"Gaussian".
An optional list specifying the hyperparameter values that define the prior
distribution. This list can be validated using the priors() function. By default,
prior is set to an empty list, thereby indicating that the hyperparameter values
should be set so that a non-informative prior distribution is obtained.
An optional positive integer specifying the number of simulation iterations after the
burn-in period. By default, n.sim is set to 500.
An optional positive integer specifying the number of burn-in iterations. By default,
n.burnin is set to 100.
An optional positive integer specifying the thinning interval. By default,
n.thin is set to 1.
An optional logical indicating whether the Stochastic Search Variable Selection (SSVS)
procedure should be applied to identify relevant lags of the output, exogenous, and threshold
series. By default, ssvs is set to FALSE.
An optional positive integer indicating the component of the output series used as the
threshold variable. By default, setar is set to NULL, indicating that the
fitted model is not a SETAR model.
An optional character string specifying the execution strategy for parallel
computation. Available options are "sequential" and "multisession". By default,
plan_strategy is set to "sequential".
An optional logical indicating whether a progress bar should be displayed during
execution. By default, progress is set to TRUE.
mtar