detectOutliersBySuperSmoother: detectOutliersBySuperSmoother

In twMisc: Utility functions of tw

Description

detect unusual local values, i.e. outliers, in univariate time series by The Hampel Filter

Usage

detectOutliersBySuperSmoother(x, maxPropResid = 2, 
    ...)

Arguments

x	numeric vector representing a time series
maxPropResid	minimum factor of resid/(interquantile-range/2) to be classified as outlier (with quantiles=(0.1,0.9))
...	further arguments to supsmu, such as bass

Details

NA values are first filled by linear interpolation before applying the smoother

Value

A list with entires

y	the corrected time series (outliers replaced by smoothed value)
ind	the indices of detected outliers
ySmooth	the filled and smoothed time series
propResid	resid/(interQuartileRange/2)

Author(s)

Thomas Wutzler

twMisc documentation built on May 2, 2019, 6:11 p.m.