coef.gets: Extraction functions for 'gets' objects

Description

Extraction functions for objects of class 'gets'

Usage

# S3 method for gets
coef(object, spec=NULL, ...)
  # S3 method for gets
fitted(object, spec=NULL, ...)
  # S3 method for gets
logLik(object, ...)
  # S3 method for gets
plot(x, spec=NULL, col=c("red","blue"),
    lty=c("solid","solid"), lwd=c(1,1), ...)
  # S3 method for gets
predict(object, spec=NULL, n.ahead=12, newmxreg=NULL,
    newvxreg=NULL, newindex=NULL, n.sim=5000, innov=NULL, probs=NULL,
    ci.levels=NULL, quantile.type=7, return=TRUE, verbose=FALSE, plot=NULL,
    plot.options=list(), ...)
  # S3 method for gets
print(x, signif.stars=TRUE, ...)
  # S3 method for gets
residuals(object, std=NULL, ...)
  # S3 method for gets
sigma(object, ...)
  # S3 method for gets
summary(object, ...)
  # S3 method for gets
vcov(object, spec=NULL, ...)

Value

coef:: a numeric vector containing parameter estimates
fitted:: a zoo object with fitted values
logLik:: a numeric, the log-likelihood (normal density)
plot:: a plot of the fitted values and the residuals
predict:: a vector of class zoo containing the out-of-sample forecasts, or a matrix of class zoo containing the out-of-sample forecasts together with prediction-quantiles, or - if return=FALSE - NULL
print:: a print of the estimation results
residuals:: a zoo object with the residuals
sigma:: the regression standard error ('SE of regression')
summary:: a print of the items in the gets object
vcov:: a variance-covariance matrix

Arguments

object: an object of class 'gets'
x: an object of class 'gets'
spec: NULL, "mean", "variance" or, in some instances, "both". When NULL is a valid value, then it is automatically determined whether information pertaining to the mean or variance specification should be returned
signif.stars: logical. If TRUE, then p-values are additionally encoded visually, see printCoefmat
std: logical. If FALSE (default), then the mean residuals are returned. If TRUE, then the standardised residuals are returned
n.ahead: integer that determines how many steps ahead predictions should be generated (the default is 12)
newmxreg: a matrix of n.ahead rows and NCOL(mxreg) columns with the out-of-sample values of the mxreg regressors
newvxreg: a matrix of n.ahead rows and NCOL(vxreg) columns with the out-of-sample values of the vxreg regressors
newindex: NULL (default) or the date-index for the zoo object returned by predict.arx. If NULL, then the function uses the in-sample index to generate the out-of-sample index
n.sim: integer, the number of replications used for the generation of the forecasts
innov: NULL (default) or a vector of length n.ahead * n.sim containing the standardised errors (that is, zero mean and unit variance) used for the forecast simulations. If NULL, then a classica bootstrap procedure is used to draw from the standardised in-sample residuals
probs: NULL (default) or a vector with the quantile-levels (values strictly between 0 and 1) of the forecast distribution. If NULL, then no quantiles are returned unless ci.levels is non-NULL
ci.levels: NULL (default) or a vector with the confidence levels (expressed as values strictly between 0 and 1) of the forecast distribution. The upper and lower values of the confidence interval(s) are returned as quantiles
quantile.type: an integer between 1 and 9 that selects which algorithm to be used in computing the quantiles, see the argument type in quantile
return: logical. If TRUE (default), then the out-of-sample predictions are returned. The value FALSE, which does not return the predictions, may be of interest if only a prediction plot is of interest
verbose: logical with default FALSE. If TRUE, then additional information (typically the quantiles and/or the simulated series) used in the generation of forecasts is returned. If FALSE, then only the forecasts are returned
plot: NULL (default) or logical. If NULL, then the value set by options$plot (see options) determines whether a plot is produced or not. If TRUE, then the out-of-sample forecasts are plotted.
plot.options: a list of options related to the plotting of forecasts, see 'Details'
col: colours of fitted (default=red) and actual (default=blue) lines
lty: types of fitted (default=solid) and actual (default=solid) lines
lwd: widths of fitted (default=1) and actual (default=1) lines
...: additional arguments

Author

Felix Pretis, https://felixpretis.climateeconometrics.org/
James Reade, https://sites.google.com/site/jjamesreade/
Moritz Schwarz, https://www.inet.ox.ac.uk/people/moritz-schwarz
Genaro Sucarrat, https://www.sucarrat.net/

Details

The plot.options argument is a list that controls the prediction plot, see 'Details' in predict.arx

Examples

Run this code

##Simulate from an AR(1):
set.seed(123)
y <- arima.sim(list(ar=0.4), 100)

##Simulate four independent Gaussian regressors:
xregs <- matrix(rnorm(4*100), 100, 4)

##estimate an AR(2) with intercept and four conditioning
##regressors in the mean, and a log-ARCH(3) in the variance:
mymod <- arx(y, mc=TRUE, ar=1:2, mxreg=xregs, arch=1:3)

##General-to-Specific (GETS) model selection of the mean:
meanmod <- getsm(mymod)

##General-to-Specific (GETS) model selection of the variance:
varmod <- getsv(mymod)

##print results:
print(meanmod)
print(varmod)

##plot the fitted vs. actual values, and the residuals:
plot(meanmod)
plot(varmod)

##generate and plot predictions of the mean:
predict(meanmod, plot=TRUE)

##print the entries of object 'gets':
summary(meanmod)
summary(varmod)

##extract coefficients of the simplified (specific) model:
coef(meanmod) #mean spec
coef(varmod) #variance spec

##extract log-likelihood:
logLik(mymod)

##extract coefficient-covariance matrix of simplified
##(specific) model:
vcov(meanmod) #mean spec
vcov(varmod) #variance spec

##extract and plot the fitted values:
mfit <- fitted(meanmod) #mean fit
plot(mfit)
vfit <- fitted(varmod) #variance fit
plot(vfit)

##extract and plot residuals:
epshat <- residuals(meanmod)
plot(epshat)

##extract and plot standardised residuals:
zhat <- residuals(varmod)
plot(zhat)

Run the code above in your browser using DataLab