shipunov (version 1.6)

Biarrows: Adds correlation arrows to the scatterplot

Description

Calculates correlations between original and derived variables and plots corresponding arrows

Usage

Biarrows(deriv, orig, coeffs=NULL, shrink=0.45, closer=0.8,
 tx=NULL, tx.col=2, tx.cex=1, tx.font=1, xpd=TRUE,
 ar.col=2, ar.len=0.1, ...)

Arguments

deriv

Data derived from, e.g., dimension reducion of 'orig'

orig

Original data

coeffs

(Optional) two-column matrix with proposed coordinates of arrow tips, row names must represent 'orig' variables

shrink

How to shrink arrows in relation to 'deriv' ranges, default is 45% (0.45)

closer

How closer to the center (in relation to the text label) is the arrow tip, default is 0.8

tx

(Optional) text labels, default are column names of 'orig'

tx.col

Color of text labels, default is 2

tx.cex

Size of text, default is 1

tx.font

Font of text, default is 1

xpd

Allow text to go outside of plotting region?

ar.col

Color of arrows, default is 2

ar.len

Length of the edges of the arrow head (in inches)

...

Further arguments to arrows()

Details

Biarrows() calculates correlations between two sets of variables which generally belong to the same data: more then one 'orig' variables and exactly two 'deriv' variables. Then is scales correlations to the 'deriv' ranges and adds text labels and arrows to the scatterplot of derived variables. These arrows represent the original variables in relation with derived variables. Resulted plot may be seen as a biplot which simultaneously shows two sets of variables.

This approach might work for data derived from (almost) any kind of dimensional reduction.

If 'deriv' data contains more then 2 variables, they will be discarded. It is supposed that 'deriv' data is centered around 0. If not, use scale() to center it (see examples). Both 'deriv' and 'orig' should be either data frames or matrices with compatible dimensions.

Biarrows(dr, coeffs=...) allows to use pre-calculated coefficients. In this case, 'data' is ignored, and 'coeffs' will be scaled. See examples to understand better how it works.

See Also

biplot

Examples

# NOT RUN {
iris.cmd <- cmdscale(dist(iris[, -5]))
plot(iris.cmd, xlab="Dim 1", ylab="Dim 2")
Biarrows(iris.cmd, iris[, -5])

# ===

library(MASS)
iris.mds <- isoMDS(dist(iris[, -5]) + 1e-9)
plot(iris.mds$points, xlab="Dim 1", ylab="Dim 2")
Biarrows(iris.mds$points, iris[, -5])

# ===

iris.p <- prcomp(iris[, -5], scale=TRUE)
biplot(iris.p, xpd=TRUE, main="Original PCA biplot")
plot(iris.p$x)
Biarrows(iris.p$x, iris[, -5])
title(main="PCA biplot with Biarrows()")

# ===

# how to use 'coeffs'
plot(iris.p$x, xlab="PCA1", ylab="PCA2")
coeffs <- cor(iris[, -5], iris.p$x, method="spearman")
Biarrows(iris.p$x, coeffs=coeffs)

# ===

plot(scale(iris[, c(1, 3)]))
Biarrows(scale(iris[, c(1, 3)]), iris.p$x)
title(main="\"Reversed biplot\"")

# ===

plot(scale(iris[, c(1, 3)]))
Biarrows(scale(iris[, c(1, 3)]), iris[, c(2, 4)])
title(main="Iris flowers: lengths vs. widths")

# }