class: Univariate GARCH Bootstrap Class

Description

Class for the univariate GARCH Bootstrap based Forecasts.

Objects from the Class

A virtual Class: No objects may be created from it.

Extends

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

Methods

as.data.frame

signature(x = "uGARCHboot"): extracts various values from object (see note).

plot

signature(x = "uGARCHboot", y = "missing"): bootstrap forecast plots.

show

signature(object = "uGARCHboot"): bootstrap forecast summary.

Note

The as.data.frame function takes optionally the arguments which, being either “sigma” or “series”, the argument type, with the options “raw” for the bootstrapped series, “summary” for summary statistics per n.ahead, and “q” for the quantiles of the n.ahead bootstrapped series, for which the option qtile is then required and takes a numeric vector of quantiles (e.g. c(0.05, 0.95) ).
The plot method provides for a Parameter Density Plots (only valid for the “full” method), and the series and sigma forecast plots with quantile error lines from the bootstrapped n.ahead distribution. The plot option which relates to either a numeric choice (1:3), an interactive choice (“ask” which is the default) and an all plot choice (“all”) for which only plots 2 and 3 are included.

Author(s)

Alexios Ghalanos

References

Pascual, L., Romo, J. and Ruiz, E. 2004, Bootstrap predictive inference for ARIMA processes, Journal of Time Series Analysis.
Pascual, L., Romo, J. and Ruiz, E. 2006, Bootstrap prediction for returns and volatilities in GARCH models, Computational Statistics and Data Analysis.

See Also

Classes uGARCHforecast, uGARCHfit and uGARCHspec.