summary.arrob: Summary of a Fitted Autoregressive Model

In robts: Robust Time Series Analysis

Description

Summary method for class "arrob".

Usage

## S3 method for class \code{arrob}
## S3 method for class 'arrob'
summary(object, correlation=FALSE, symbolic.cor=FALSE, ...)

## S3 method for class \code{summary.arrob}
## S3 method for class 'summary.arrob'
print(x, digits = max(3L, getOption("digits") - 3L), symbolic.cor = x$symbolic.cor, 
    signif.stars = getOption("show.signif.stars"), ...)

Arguments

object	an object of class "arrob", usually, a result of a call to arrob.
x	an object of class "summary.arrob", usually, a result of a call to summary.arrob.
correlation	logical; if TRUE, the correlation matrix of the estimated AR parameters is returned and printed.
digits	the number of significant digits to use when printing.
symbolic.cor	logical. If TRUE, print the correlations in a symbolic form (see symnum) rather than as numbers.
signif.stars	logical. If TRUE, ‘significance stars’ are printed for each coefficient.
...	further arguments are currently ignored. Only for compatibility with generic function.

Details

Standard errors and correlation matrix of the coefficients can only be calculated if one sets asyvar=TRUE in the function arrob. In this case they are determined by a block bootstrap. Theoretical results to the consistency of this method are missing yet, so these values should be taken with care just as the printed p-values which are based on the asymptotic normality of the estimators which is also not formally proofed yet.

Value

Object of classes "summary.arrob". This is a list consisting of:

residuals	numeric vector of estimated residuals.
method	character string indicating the used eestimation method.
order	numeric value giving the order of the fitted autoregressive model.
estsig	numerical value giving the estimated scsle of the innovations.
mean	numerical value giving the estimated location of the time series.
coefvar	matrix of the estimated covariance of the AR parameters.
n	numerical value giving the number of observations.
corp	logical indicating whether correlation between the estimaed paramters should be determined.
cor	matrix of estimated correlation betweeb the AR parameters.
symbolic.cor	logical indicating whether cor should be printed as symbols.

Author(s)

Alexander Dürre

References

Lahiri, S.N. (1999): Theoretical Comparisons of Block Bootstrap Methods, The annals of Statistics, vol. 27, 386–404.

See Also

Robust estimation of autoregressive processes arrob.

Examples

set.seed(1066)
tss <- arima.sim(model = list(ar = 0.3, ma = 0.5), n = 100)
summary(arrob(tss, method = "yw"))

robts documentation built on May 2, 2019, 4:55 p.m.