methods-volatility function

Extract GARCH model volatility

Extracts volatility from a fitted GARCH object. methods

## S3 method for class 'fGARCH'
volatility(object, type = c("sigma", "h"), ...)

Arguments

• object: an object of class "fGARCH" as returned by garchFit().
• type: a character string denoting if the conditional standard deviations "sigma" or the variances "h" should be returned.
• ...: currently not used.

Details

volatility is an S3 generic function for computation of volatility, see volatility for the default method.

The method for "fGARCH" objects, described here, extracts the volatility from slot @sigma.t or @h.t of an "fGARCH" object usually obtained from the function garchFit().

The class of the returned value depends on the input to the function garchFit who created the object. The returned value is always of the same class as the input object to the argument data in the function garchFit, i.e. if you fit a "timeSeries"

object, you will get back from the function fitted also a "timeSeries" object, if you fit an object of class "zoo", you will get back again a "zoo" object. The same holds for a "numeric" vector, for a "data.frame", and for objects of class "ts", "mts".

In contrast, the slot itself always contains a numeric vector, independently of the class of the input data input, i.e. the function call slot(object, "fitted") will return a numeric vector.

Author(s)

Diethelm Wuertz for the Rmetrics -port

Note

(GNB) Contrary to the description of the returned value of the "fGARCH" method, it is always "numeric".

TODO: either implement the documented behaviour or fix the documentation.

Methods

Methods for volatility defined in package fGarch:

• object = "fGARCH": Extractor function for volatility or standard deviation from an object of class "fGARCH".

See Also

garchFit, class fGARCH

Examples

## Swiss Pension fund Index -
   stopifnot(require("timeSeries")) # need package 'timeSeries'
   x = as.timeSeries(data(LPP2005REC, package = "timeSeries"))

## garchFit
   fit = garchFit(LPP40 ~ garch(1, 1), data = 100*x, trace = FALSE)
   fit

## volatility -
   # Standard Deviation:
   vola = volatility(fit, type = "sigma")
   head(vola)
   class(vola)
   # Variance:
   vola = volatility(fit, type = "h")
   head(vola)
   class(vola)

## slot -
   vola = slot(fit, "sigma.t")
   head(vola)
   class(vola)
   vola = slot(fit, "h.t")
   head(vola)
   class(vola)