Provides functions for the selection of extreme value threshold. At the moment only the simplest case, where the data can be treated as independent identically distributed observations, is considered. Future releases will tackle more general situations. See the 'threshr' website for more information, documentation and examples.

Details

The main function in the threshr package is ithresh, which uses leave-one-out cross-validation in a Bayesian setup to compare the predictive ability resulting from the use of each of a user-supplied set of thresholds.

See vignette("threshr-vignette", package = "threshr") for an overview of the package.

References

Northrop, P. J. (2017). revdbayes: Ratio-of-Uniforms Sampling for Bayesian Extreme Value Analysis. R package version 1.2.1. https://cran.r-project.org/package=revdbayes.

Northrop, P. J., Attalides, N. and Jonathan, P. (2017) Cross-validatory extreme value threshold selection and uncertainty with application to ocean storm severity. Journal of the Royal Statistical Society Series C: Applied Statistics, 66(1), 93-120. doi:10.1111/rssc.12159

See also

The packages revdbayes and rust.

ithresh for threshold selection in the i.i.d. case based on leave-one-out cross-validation.

Author

Maintainer: Paul J. Northrop p.northrop@ucl.ac.uk [copyright holder]

Authors:

  • Nicolas Attalides