MFT (version 2.0)

MFT.filterdata: MFT.filterdata

Description

Naive routine to remove trend from the data.

Usage

MFT.filterdata(x, filterwidth = NULL, filtersigma = NULL)

Arguments

x

numeric vector, input sequence of random variables.

filterwidth

postive interger, < length(x)/2, number of data points left and right of the current value that are taken into account for Gaussian smoothing.

filtersigma

numeric, > 0, standard deviation of Gassian kernel.

Value

invisible

xfiltered

filtered data (for filtering the first and last (filterwidth many) data points of the original series cannot be evaluated and are omited)

xraw

orignal data, but the first and last (filterwidth many) data point are omitted

xtrend

trend that is removed by filtering. That is xfiltered = xraw - xtrend

x

orignal data

filterwidth

number of data points left and right of the current value that are taken into account for Gaussian smoothing

filtersigma

standard deviation of the Gaussian kernel

References

Michael Messer, Hendrik Backhaus, Albrecht Stroh and Gaby Schneider (2019+). Peak detection in times series

See Also

MFT.peaks, plot.MFT, summary.MFT, MFT.rate, MFT.variance, MFT.mean

Examples

# NOT RUN {
set.seed(0)
# Normally distributed sequence with negative trend
x <- rnorm(1000,mean=seq(5,0,length.out=1000))
MFT.filterdata(x)
MFT.filterdata(x,filterwidth=200,filtersigma=200)

# }