# concatMulTS: ConcatMulTS Concatenates separated time series (of single or... In GPoM: Generalized Polynomial Modelling

 concatMulTS R Documentation

## ConcatMulTS Concatenates separated time series (of single or multiples variables)

### Description

The aim of this code is to provide, from multiple sets of (single or multiple) time series, a single concatenated set of time series for applying the global modeling technique to all the time time series in association.

### Usage

``````concatMulTS(svrlTS, winL = 9)
``````

### Arguments

 `svrlTS` All separated sets of time series. `winL` Total number of points used for computing the derivatives of the input time series. This parameter will be used as an input in function `drvSucc` to compute the derivatives.

### Value

`concaTS` A single set of concatenated time series.

### Author(s)

Sylvain Mangiarotti, Mireille Huc

### References

S. Mangiarotti, F. Le Jean, M. Huc & C. Letellier, 2016. Global modeling of aggregated and associated chaotic dynamics, Chaos, Solitons & Fractals, 83, 82-96.

### Examples

``````# load data
data("svrlTS")
# Concatenate the data set into a single time series
winL = 55
concaTS <- concat(svrlTS, winL = winL)
# Plot the concatenated time series
plot(concaTS\$sglTS\$TS[,1], concaTS\$sglTS\$TS[,2],
main = 'Concatenated time series',
xlab = 'Time (concatenated)', ylab = 'y(t)',
type = 'l', col = 'gray')
lines(concaTS\$sglTS\$TS[concaTS\$sglTS\$W == 1,1],
concaTS\$sglTS\$TS[concaTS\$sglTS\$W == 1,2], type = 'p', col = 'green', cex = 0.5)
lines(concaTS\$sglTS\$TS[concaTS\$sglTS\$W == 0,1],
concaTS\$sglTS\$TS[concaTS\$sglTS\$W == 0,2], type = 'p', col = 'red', cex = 0.5)
lines(concaTS\$sglTS\$TS[,1], concaTS\$sglTS\$W, type = 'l')

# The concatenated data set can be used for global modelling:
GPout1 <- gPoMo(data = concaTS\$sglTS\$TS[,2], tin = concaTS\$sglTS\$TS[,1],
dMax = 2, nS = 3, winL = winL, weight = concaTS\$sglTS\$W, show = 1,
IstepMin = 10, IstepMax = 6000, nPmin = 11, nPmax = 11, method = 'rk4')

``````

GPoM documentation built on July 9, 2023, 6:23 p.m.