SVDplot {rainbow}

Singular value decomposition plot

Description

The singular value decomposition (SVD) plot of Zhang et al. (2007) captures the changes in the singular columns as the number of curves gradually increases.

Usage

SVDplot(object, order = 3, plot = TRUE, plot.type = c("fts", "image"),
        mfrow = c(2, 3))

Arguments

object

An object of fds.

order

Number of Singular Value Decomposition (SVD) components. The maximum order is 4.

plot

Is graphical display required?

plot.type

Plot functional time series or images?

mfrow

Grid of graphics.

Details

By using the SVD, Zhang et al. (2007) proposed a plot for visualizing patterns of functional time series. They considered a set of curves as a two-way (p * n) data matrix, where p is the total number of covariates and n is the total number of curves.

The main advantage of this dynamic plot is to visualize both column and row information of a two-way matrix simultaneously, relate the matrix to the corresponding curves, show local variations, and highlight interactions between columns and rows of a two-way matrix.

Value

When plot = TRUE, it returns a plot.

When plot = FALSE, it returns the following:

svds

A number of singular value decomposition ordered by the amount of explained variation.

reconstruction

Reconstruction of the original data using the SVD.

residual

Residual of the original data.

Note

MATLAB code is available at https://www.stat.purdue.edu/~lingsong/.

Using the animate package of Grahn(2011), a set of dynamic movies can be created to visualize the changes in singular rows and singular columns.

Author(s)

Han Lin Shang. Please, report bugs and suggestions to [e-mail]

References

L. Zhang, J. Marron, H. Shen and Z. Zhu (2007) "Singular value decomposition and its visualization", Journal of Computational and Graphical Statistics, 16(4), 833-854.

A. Grahn (2011) "The animate Package", https://ctan.org/pkg/animate?lang=en.

See Also

fboxplot, svd

Examples

SVDplot(ElNino_OISST_region_1and2)
SVDplot(ElNino_OISST_region_1and2, plot.type = "image")