# class: Univariate GARCH Parameter Distribution Class

### Description

Class for the univariate GARCH Parameter Distribution.

### Objects from the Class

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

### Extends

Class `"GARCHdistribution"`

, directly.
Class `"rGARCH"`

, by class "GARCHdistribution", distance 2.

### Methods

- as.data.frame
`signature(x = "uGARCHdistribution")`

: Extracts various values from object (see note).- plot
`signature(x = "uGARCHdistribution", y = "missing")`

: Parameter Distribution Plots.- show
`signature(object = "uGARCHdistribution")`

: Parameter Distribution Summary.

### Note

The `as.data.frame`

function takes optionally 2 additional arguments,
namely `window`

which indicates the particular distribution window number
for which data is required (is usually just 1 unless the recursive option was
used), and `which`

indicating the type of data required. Valid values for
the latter are “rmse” for the root mean squared error between simulation
fit and actual parameters, “stats” for various statistics computed for
the simulations such as log likelihood, persistence, unconditional variance and
mean, “coef” for the estimated coefficients (i.e. the parameter
distribution and is the default choice), and “coefse” for the estimated
robust standard errors of the coefficients (i.e. the parameter standard error
distribution).

The plot method offers 4 plot types, namely, Parameter Density Plots (take
`window`

as additional argument), Bivariate Plots (take `window`

as
additional argument), Stats and RMSE (only when recursive option used) Plots.
The standard option for `which`

is used, allowing for a numeric arguments
to one of the four plot types else interactive choice via “ask”.

### Author(s)

Alexios Ghalanos

### See Also

Classes `uGARCHforecast`

, `uGARCHfit`

and
`uGARCHspec`

.

### Examples

1 2 3 4 5 6 7 8 9 10 11 12 | ```
## Not run:
data(sp500ret)
spec = ugarchspec(variance.model=list(model="gjrGARCH", garchOrder=c(1,1)),
mean.model=list(armaOrder=c(1,1), arfima=FALSE, include.mean=TRUE,
archm = FALSE, archpow = 1), distribution.model="std")
fit = ugarchfit(data=sp500ret[, 1, drop = FALSE], out.sample = 0,
spec = spec, solver = "solnp")
dist = ugarchdistribution(fit, n.sim = 2000, n.start = 50, m.sim = 5)
## End(Not run)
``` |