Skip to contents

This function implements the automated proposal from Section 2.2 of Langousis et al. (2016) for mean residual life plots. It returns the threshold that minimize the weighted mean square error and moment estimators for the scale and shape parameter based on weighted least squares.

Usage

automrl(xdat, kmax, thresh, plot = TRUE, ...)

Arguments

xdat

[numeric] vector of observations

kmax

[integer] maximum number of order statistics

thresh

[numeric] vector of thresholds; if missing, uses all order statistics from the 20th largest until kmax as candidates

plot

[logical] if TRUE (default), return a plot of the mean residual life plot with the fitted slope and the chosen threshold

...

additional arguments, currently ignored

Value

a list containing

  • threshselected threshold

  • scalescale parameter estimate

  • shapeshape parameter estimate

Details

The procedure consists in estimating the usual

References

Langousis, A., A. Mamalakis, M. Puliga and R. Deidda (2016). Threshold detection for the generalized Pareto distribution: Review of representative methods and application to the NOAA NCDC daily rainfall database, Water Resources Research, 52, 2659--2681.