diss.PER: Periodogram Based Dissimilarity

In TSclust: Time Series Clustering Utilities

Periodogram Based Dissimilarity

Description

Computes the distance between two time series based on their periodograms.

Usage

diss.PER(x, y, logarithm=FALSE, normalize=FALSE)

Arguments

x	Numeric vector containing the first of the two time series.
y	Numeric vector containing the second of the two time series.
logarithm	Boolean. If TRUE logarithm of the periodogram coefficients will be taken.
normalize	Boolean. If TRUE, the periodograms will be normalized by the variance of their respective series.

Details

Computes the Euclidean distance between the periodogram coefficients of the series x and y. Additional transformations can be performed on the coefficients depending on the values of logarithm and normalize.

Value

The computed distance.

Author(s)

Pablo Montero Manso, José Antonio Vilar.

References

Caiado, J., Crato, N. and Peña, D. (2006) A periodogram-based metric for time series classification. Comput. Statist. Data Anal., 50(10), 2668–2684.

Montero, P and Vilar, J.A. (2014) TSclust: An R Package for Time Series Clustering. Journal of Statistical Software, 62(1), 1-43. \Sexpr[results=rd]{tools:::Rd_expr_doi("doi:10.18637/jss.v062.i01")}

See Also

link{diss.INT.PER}

Examples

## Create three sample time series
x <- cumsum(rnorm(100))
y <- cumsum(rnorm(100))
z <- sin(seq(0, pi, length.out=100))
## Compute the distance and check for coherent results
diss.PER(x, y)
diss.PER(x, z)
diss.PER(y, z)
diss.PER(x, y, TRUE, TRUE)
diss.PER(x, z, TRUE, TRUE)
diss.PER(y, z, TRUE, TRUE)
#create a dist object for its use with clustering functions like pam or hclust
diss( rbind(x,y,z), "PER", logarithm=TRUE, normalize=TRUE)

TSclust documentation built on June 8, 2025, 11:05 a.m.