wcc-package: wcc

In wcc: Windowed Cross Correlation

wcc

Description

Functions for Windowed Cross Correlation.

Details

Calculates Windowed Cross Correlation for estimating association between pairs of nonstationary time series. Provides support for surrogate analysis for nonparametric test of significance. Calculates aggregate statistics over a range of parameter values. Plots the results as wcc plots and heat maps.

Author(s)

Steven Boker, Minquan Xu, Sareena Chadha, Christopher Welker, Jingyun Wu, Pascal Deboeck

Maintainer: Steven Boker <[e-mail]>

References

Boker, S. M., Rotondo, J. L., Xu, M., & King, K. (2002). Windowed cross-correlation and peak picking for the analysis of variability in the association between behavioral time series. Psychological methods, 7(3), 338.

Moulder, R., Boker, S., Ramseyer, F., & Tschacher, W. (2018). Determining synchrony between behavioral time series: An application of surrogate data generation for establishing falsifiable null-hypotheses. Psychological Methods. 23:4 pp 757–773

See Also

See wccCalc for the core function that calculates a windowed cross correlation matrix.
See wccPeakPick for the core function that estimates time lag of maximum association from a windowed cross correlation matrix.
See wccAggregate to call wccCalc and wccPeakPick and then calculate aggregate statistics from a windowed cross correlation matrix.
See wccPlot to plot a section of a windowed cross correlation matrix and peak picking line from a file created by wccAggregate.
See wccSurrogateDyads to generate a distribution of the aggregate statistics conforming to the null hypothesis that the pairing of the dyad does not matter.
See wccFindDyadParam to explore a range of parameter values for wccCalc that are compared between surrogate and real dyads.
See wccHeatmap to visualize results of selected aggregated statistics for combinations of parameters calculated by wccFindDyadParam.

Examples

#Create a windowed cross correlation plot
tSeries1 <- sin(c(1:1000)/10) + rnorm(1000, mean=0, sd=.5)
tSeries2 <- sin(1+c(1:1000)/10) + rnorm(1000, mean=0, sd=.5)
wccPlot(inSeries1=tSeries1, inSeries2=tSeries2, startwindow=1, endwindow=500, 
    wMax=100, tMax=100, wInc=1, tInc=1, Lsize=8, pspan=.25, type="Max", 
    samplespersecond=10)

# Create two arrays of timeseries with dyadic dependence
array1 <- matrix(NA, nrow=10, ncol=500)
array2 <- matrix(NA, nrow=10, ncol=500)
for(i in 1:10) {
    array1[i,] <- sin(c(1:500)/runif(1, min=5, max=20)) + rnorm(500, mean=0, sd=.5)
    array2[i,] <- array1[i,] + rnorm(500, mean=0, sd=.5)
}
# Select parameters to explore
wMaxVec <- c(50,100)
tMaxVec <- c(25,50)
wccFDPout <- wccFindDyadParam(inArray1=array1, inArray2=array2, wMaxvector=wMaxVec,
    tMaxvector=tMaxVec, nSurrogates=30, samplespersecond=1, method="r")
# Plot a heatmap
wccHeatmap(xparam=wccFDPout$wMax, yparam=wccFDPout$tMax, aggstat=wccFDPout$maxMean,
    xlabel="Window Max", ylabel="Max Lag")

wcc documentation built on July 14, 2026, 5:07 p.m.