InterpolateOutliers: InterpolateOutliers

In Mthrun/TSAT: Time Series Analysis Tools (TSAT)

InterpolateOutliers

Description

Interpolates Outliers setting them NaN and then applying spline interpolation

Usage

InterpolateOutliers(Time, Datavector, OutliersTime, option = "stine",

PlotIt = TRUE)

Arguments

Time	[1:n] vector of time, POSIXlt or POSIXct are accepted
Datavector	[1:n] numerical vector of data
OutliersTime	[1:k] vector of time of outliers, in the format of the Time values
option	see na_interpolation
PlotIt	Default: FALSE, TRUE: Evaluates output of function versus input by plots

Details

Assumption is that outliers should be ignore in timeseries analysis.

Value

[1:n] interpolated vector of data

Author(s)

Michael Thrun

See Also

In case of missing data, e.g. NA values, see InterpolateMissingValues instead

Examples

data(airquality)

ind = which(is.finite(airquality$Solar.R))

# Remove non finite values or alternatively, interpolate missing values:
# data = InterpolateMissingValues(dates, airquality$Solar.R)
date_strings = paste("1973", airquality$Month[ind], airquality$Day[ind], sep = "-")
dates = as.Date(date_strings)

data = airquality$Solar.R[ind]
res = WaveletOutlierDetection(data)
outliersInd = which(res!=0)

vals = InterpolateOutliers(dates,data,dates[outliersInd])

Mthrun/TSAT documentation built on Feb. 5, 2024, 11:15 p.m.