ctbi.cycle {ctbi}

ctbi.cycle

Description

Calculate the mean (or median) stack of the detrended data for all bins, and add the cyclic component column to data0.

Usage

ctbi.cycle(data0, bin.size, outliers.checked)

Arguments

data0

data.table with the columns x (time series), y (values), time.bin (position of x between 0 and 1 with respect to the bin boundaries), cycle.index (index between 1 and bin.size attached to time.bin), and long.term (the long-term trend)

bin.size

median number of points within all non-empty bins

outliers.checked

boolean to indicate if the median (outliers.checked = FALSE) or the mean (outliers.checked = TRUE) should be used to calculate the stack

Value

A list that contains data0 (data0.l) and a data.table that contains the mean (or median) stack of all accepted bins (FUN.cycle.l)

Examples

library(data.table)
x <- seq(from=as.Date('2001-01-01'),to=as.Date('2010-12-01'),by='1 month')
y <- 3*cos(2*pi*(0:(length(x)-1))/12)+runif(length(x))
bin.size <- 12
outliers.checked <- TRUE
time.bin <- rep(((1:bin.size)/bin.size)-(1/(2*bin.size)),10)
cycle.index <- findInterval(time.bin,(1:(bin.size-1))/bin.size)+1
long.term <- rep(0,length(x))
data0 <- data.table(x=x,y=y,cycle.index=cycle.index,long.term=long.term,time.bin=time.bin)
list.cycle <- ctbi.cycle(data0,bin.size,outliers.checked)
data0.with.cyclic.component <- list.cycle$data0.l
mean.cycle <- list.cycle$FUN.cycle.l