uGARCHfilter-class {rugarch}

class: Univariate GARCH Filter Class

Description

Class for the univariate GARCH filter.

Extends

Class "GARCHfilter", directly. Class "rGARCH", by class "GARCHfilter", distance 2.

Methods

fitted

signature(object = "uGARCHfilter"): Extracts the fitted values.

residuals

signature(object = "uGARCHfilter"): Extracts the residuals. Optional logical argument standardize (default is FALSE) allows to extract the standardized residuals.

sigma

signature(object = "uGARCHfilter"): Extracts the conditional sigma values.

coef

signature(object = "uGARCHfilter"): Extracts the coefficients.

infocriteria

signature(object = "uGARCHfilter"): Calculates and returns various information criteria.

newsimpact

signature(object = "uGARCHfilter"): Calculates and returns the news impact curve.

likelihood

signature(object = "uGARCHfilter"): Extracts the likelihood.

signbias

signature(object = "uGARCHfilter"): Calculates and returns the sign bias test of Engle and Ng (1993).

gof

signature(object = "uGARCHfilter", groups = "numeric"): Calculates and returns the adjusted goodness of fit statistic and p-values for the fitted distribution based on the Vlaar and Palm paper (1993). Groups is a numeric vector of bin sizes.

persistence

signature(object = "uGARCHfilter", pars = "missing", distribution = "missing", model = "missing", submodel = "missing"): Calculates and returns the persistence of the garch filter model.

halflife

signature(object = "uGARCHfilter", pars = "missing", distribution = "missing", model = "missing"): Calculates and returns the halflife of the garch fit variance given a uGARCHfilter object.

uncmean

signature(object = "uGARCHfilter"): Calculates and returns the unconditional mean of the conditional mean equation (constant, ARMAX, arch-in-mean).

uncvariance

signature(object = "uGARCHfilter", pars = "missing", distribution = "missing", model = "missing", submodel = "missing"): Calculates and returns the long run unconditional variance of the garch filter given a uGARCHfilter object.

quantile

signature(x = "uGARCHfilter"): Calculates and returns, given a vector of probabilities (additional argument “probs”), the conditional quantiles of the filtered object (x).

pit

signature(object = "uGARCHfilter"): Calculates and returns the conditional probability integral transform given the data and estimated density.

plot

signature(x = "uGARCHfilter", y = "missing"): Filter plots

show

signature(object = "uGARCHfilter"): Filter summary.

Note

The uGARCHfilter class contains almost all the methods available with the uGARCHfit with the exception of those requiring the scores of the likelihood (i.e the optimization process) such as the nyblom test.

Author(s)

Alexios Ghalanos

Examples

## Not run: 
data(dji30ret)
ctrl = list(rho = 1, delta = 1e-8, outer.iter = 100, inner.iter = 650, 
tol = 1e-6)
spec = ugarchspec(variance.model = list(model = "sGARCH", garchOrder = c(1,1)), 
		mean.model = list(armaOrder = c(1,1), include.mean = TRUE), 
		distribution.model = "std")
sgarch.fit = ugarchfit(data = dji30ret[,"AA",drop=FALSE], spec = spec, 
		solver = "solnp", solver.control = ctrl)
		
spec = ugarchspec(variance.model = list(model = "sGARCH", garchOrder = c(1,1)), 
		mean.model = list(armaOrder = c(1,1), include.mean = TRUE), 
		distribution.model = "std", fixed.pars = as.list(coef(sgarch.fit)))
sgarch.filter = ugarchfilter(data = dji30ret[,"AA",drop=FALSE], spec = spec)

c(likelihood(sgarch.filter), likelihood(sgarch.fit))
c(uncmean(sgarch.filter), uncmean(sgarch.fit))
c(uncvariance(sgarch.filter), uncvariance(sgarch.fit))

## End(Not run)