Create an instance of the QPBoot
class by doing 3 things
Estimates a parametric model
from a given set of data
,
this estimate can be overwritten by using the parameter fix.param
Simulates from that model
and computes the smoothed Quantile
Periodogram (smoothedPG) for each simulated time
series and the given data
Returns an object of the class QPBoot with the calculated smoothed Periodograms
qpBoot(data, model = getARMA(list(ar.order = 2, ma.order = 0)),
levels = c(0.1, 0.5, 0.9), frequencies = 2 * pi/length(data) *
0:(length(data) - 1), weight = kernelWeight(bw = 0.1), SimNum = 1000,
fix.param = NULL)
numeric vector, containing the time-series data
an object from the class tsModel-class.
numeric vector containing values between 0 and 1 for which the smoothedPG. Will be estimated. These are the quantiles levels that are used for the validation
a vector containing frequencies at which to determine the smoothed periodogram.
an object of the class KernelWeight that is used to in the estimation of the smoothedPG.
number of bootstrap
defaults to NULL
. In this case the parameters for the simulations are
estimated via the methode defined in the argument model
. If this is not
NULL
, it has to contain a list that can be used to set the parameters
in the tsModel-class. All simulations are then done with these fixed parameters.