tsclean: Identify and replace outliers and missing values in a time series
Description
Uses loess for non-seasonal series and a periodic stl decompostion
with seasonal series to identify and replace outliers. To estimate missing values,
linear interpolation is used for non-seasonal series, and a periodic stl decompostion is used
with seasonal series.
Usage
tsclean(x, replace.missing = TRUE, lambda = NULL)
Arguments
x
time series
replace.missing
If TRUE, it not only replaces outliers, but also interpolates missing values
lambda
a numeric value giving the Box-Cox transformation parameter