rankRankPlot: Rank-rank Plot

Description

Generate rank-rank plots for ranking comparison.

Usage

rankRankPlot(object, id.col = FALSE, p.size = 1.5, p.nudge = 0.05,
             s.width = 0.5,  lab.size = 3.88,
             max.overlaps = 10, max.tick = 50,
             ref.lab = "Reference ranking", alt.lab = "Alternative ranking",
             y.lab = NULL, combine = FALSE, nr = NULL, nc = NULL)

Value

A plot comparing two rankings connected by segments. In case object$time

is not NULL, a list of plots for different time factors and the combined grid (if combine = TRUE) will be returned. The function does not print the return if it is assigned to an object. Use print with the storing object to generate the plot.

Arguments

object: an object of class "rankComp", usually, an output of a call to rankComp.
id.col: a logical value indicating whether the rank-rank segment should be colored by unit identifiers. It is not recommended if having more than 20 units.
p.size: size of segment endpoints.
p.nudge: horizontal adjustment value to nudge the starting position of labels.
s.width: line width for rank-rank segments.
lab.size: label size value.
max.overlaps: a value to exclude the label if it has too many overlaps. The default value is 10. Set max.overlaps = Inf to always show all labels.
max.tick: a positive integer to control the maximum number of axis ticks. The default value is 50. Set max.tick equal to or greater than the number of rankings to display all rankings on the axis.
ref.lab: name of the reference index.
alt.lab: name of the alternative index.
y.lab: label of the y-axis.
combine: a logical value indicating whether to generate a grid that combines plots from different time factors (If object$time is not NULL).
nr: (optional) number of rows in the plot grid.
nc: (optional) number of columns in the plot grid.

Author

Viet Duong Nguyen, Chiara Gigliarano, Mariateresa Ciommi

Examples

Run this code

data(bli)

# Goalpost normalization
bli.pol = c("neg", "pos", "pos", "pos", "pos", "neg",
            "pos", "pos", "pos", "neg", "pos")
bli.norm.2014 <- normalize(inds = bli[, 3:13], method = "goalpost",
                           ind.pol = bli.pol, time = bli$YEAR,
                           ref.time = 2014)

# Composite indices
ci.gini <- giniCI(bli.norm.2014, method = "gini",
                  ci.pol = "pos", time = bli$YEAR, ref.time = 2014,
                  only.ci = TRUE)
ci.reci <- giniCI(bli.norm.2014, method = "reci", agg = "geo",
                  ci.pol = "pos", time = bli$YEAR, ref.time = 2014,
                  only.ci = TRUE)

# Ranking comparison plots
ci.comp <- rankComp(ci.gini, ci.reci, id = bli$COUNTRY, time = bli$YEAR)
rankScatterPlot(ci.comp)$'2014'
rankShiftPlot(ci.comp)$'2015'
rankRankPlot(ci.comp)$'2016'

# Storing and printing
p.scatter <- rankScatterPlot(ci.comp, combine = TRUE, max.overlaps = 20)
print(p.scatter$'2017') # or: print(p.scatter[[4]])
print(p.scatter$'comb') # or: print(p.scatter[[5]])