threshr: Threshold Selection and Uncertainty for Extreme Value Analysis

Provides functions for the selection of thresholds for use in extreme value models, based mainly on the methodology in Northrop, Attalides and Jonathan (2017) <doi:10.1111/rssc.12159>. It also performs predictive inferences about future extreme values, based either on a single threshold or on a weighted average of inferences from multiple thresholds, using the 'revdbayes' package <>. At the moment only the case where the data can be treated as independent identically distributed observations is considered.

Package details

AuthorPaul J. Northrop [aut, cre, cph], Nicolas Attalides [aut]
MaintainerPaul J. Northrop <>
LicenseGPL (>= 2)
Package repositoryView on CRAN
Installation Install the latest version of this package by entering the following in R:

Try the threshr package in your browser

Any scripts or data that you put into this service are public.

threshr documentation built on May 1, 2019, 6:34 p.m.