plot_local.multiple.cross.regression: Auxiliary routine for plotting local multiple...

Description Usage Arguments Details Value Author(s) References

Description

Produces a plot of local multiple cross-regressions.

Usage

1
plot_local.multiple.cross.regression(Lst, lmax, nsig=2, xaxt="s")

Arguments

Lst

A list from local.multiple.cross.regression.

lmax

maximum lag (and lead).

nsig

An optional value for the number of significant variables to plot_ Default is 2.

xaxt

An optional vector of labels for the "x" axis. Default is 1:n.

Details

The routine produces time series plots of local multiple cross-regressions with their confidence interval for every lag and lead. Also, at every upturn and downturn of the corresponding local multiple cross-correlation, the name of the variable that maximizes that multiple correlation against the rest is shown on top. The others are named ordered by significance when they are relevant.

Value

Plot.

Author(s)

Javier Fernández-Macho, Dpt. of Quantitative Methods, University of the Basque Country, Agirre Lehendakari etorb. 83, E48015 BILBAO, Spain. (email: javier.fernandezmacho at ehu.eus).

References

Fernández-Macho, J., 2018. Time-localized wavelet multiple regression and correlation, Physica A: Statistical Mechanics, vol. 490, p. 1226–1238. <DOI:10.1016/j.physa.2017.11.050>


wavemulcor documentation built on July 1, 2020, 5:10 p.m.