decluster: Decluster a Time Series

In usnistgov/potMax: Empirical Calculation of the Distribution of the Maximum from a Peaks Over Threshold Process

Description

Decluster a time series by forming clusters and returning only cluster maximums

Usage

decluster(complete_series, obs_times = NULL)

Arguments

complete_series	(numeric vector) The time series.
obs_times	(numeric vector or NULL) If NULL, ignored; otherwise, the observed times of the values in complete_series. When non NULL, the times associated with cluster maximums are also returned.

Details

Clusters are formed by sequential observations above the series mean value. All observations below the mean value are discarded. Cluster maximums are returned.

Value

An S3 object of class declustered_series with components

$declustered_series

The cluster maximums.

$declustered_times

If obs_times is non NULL, the observed times of the cluster maximums; otherwise NULL.

Examples

complete_series <- -jp1tap1715wind270$value

declustered_obs <- decluster(complete_series)

usnistgov/potMax documentation built on May 3, 2019, 2:38 p.m.