compareBars: Produces comparison stacked bar charts for two sets of groups

In ralmond/CPTtools: Tools for Creating Conditional Probability Tables

Produces comparison stacked bar charts for two sets of groups

Description

This produces set of stacked bar charts grouped for comparison between two groups. For example, if suppose that there is a set of probabilities over a collection of proficiency variables measures both before and after obtaining a certain piece of evidence. The compareBars function would produce stacked bar charts which compare the prior and posterior probabilities for each variable.

Usage

compareBars(data1, data2, profindex,
            groupNames = c(deparse(data1), deparse(data2)), ...,
            ylim = c(min(offsets) - 0.25, max(1 + offsets)),
            cex.names = par("cex.axis"), digits = 2, legend.loc = c(0,1),
            legend.cex = par("cex"), col = par("col"), col1 = NULL,
            col2 = NULL, main = NULL, sub = NULL, xlab = NULL,
            ylab = NULL, rotlab = FALSE)

compareBars2(data1, data2, profindex,
             groupNames=c("Prior","Post"), error.bars=2, scale=100,
             err.col="gray20", ..., ylim = NULL) 

Arguments

data1	Data set with first (prior) values
data2	Data set with second (posterior) values
profindex	Index of one of the proficiency levels which will be used as the baseline for the stacked bar charts.
groupNames	Names of the groups represented by data1 and data2 respectively.
...	Other arguments to barplot.
ylim	Default limits for Y axis.
cex.names	Character magnification for names.
digits	Number of digits for overlaid numeric variables.
legend.loc	Location for legend, see legend.
legend.cex	Character magnification for legend.
col	The normal graphics col parameter (see par, passed through to other graphics operators using .... Is also the default for col1 and col2 if those values are not supplied.
col1	Color scale for the first data set. This should be a vector of colors equal to the number of groups.
col2	Color scale for the second data set. This should be a vector of colors equal to the number of groups.
main	Character scalar giving main title (see title).
sub	Character scalar giving sub title (see title).
xlab	Character scalar giving x-axis label (see title).
ylab	Character scalar giving x-axis label (see title).
rotlab	If TRUE labels are rotated 90 degrees.
error.bars	The number of standard errors for error bars.
err.col	The color for error bars.
scale	Scales data as probabilities (scale=1) or percentages (scale=100).

Value

Invisibly returns the x-co-ordinates of the bars.

Note

The function compareBars2 is a somewhat experimental extension to compareBars which adds error bars to the posterior. The result is not entirely satisfactory, and this function may change with future releases.

Author(s)

Russell Almond

References

Almond, R. G., Shute, V. J., Underwood, J. S., and Zapata-Rivera, J.-D (2009). Bayesian Networks: A Teacher's View. International Journal of Approximate Reasoning. 50, 450-460.

See Also

stackedBars, colorspread, buildFactorTab, barplot

Examples

margins.prior <- data.frame (
 Trouble=c(Novice=.19,Semester1=.24,Semester2=.28,Semseter3=.20,Semester4=.09),
 NDK=c(Novice=.01,Semester1=.09,Semester2=.35,Semseter3=.41,Semester4=.14),
 Model=c(Novice=.19,Semester1=.28,Semester2=.31,Semseter3=.18,Semester4=.04)
)

margins.post <- data.frame(
 Trouble=c(Novice=.03,Semester1=.15,Semester2=.39,Semseter3=.32,Semester4=.11),
 NDK=c(Novice=.00,Semester1=.03,Semester2=.28,Semseter3=.52,Semester4=.17),
 Model=c(Novice=.10,Semester1=.25,Semester2=.37,Semseter3=.23,Semester4=.05))

foo <-
compareBars(margins.prior,margins.post,3,c("Prior","Post"),
            main="Margins before/after Medium Trouble Shooting Task",
            sub="Observables:  cfgCor=Medium, logCor=High, logEff=Medium",
            legend.loc = "topright",
            cex.names=.75, col1=hsv(h=.1,s=.2*1:5-.1,alpha=1),
            col2=hsv(h=.6,s=.2*1:5-.1,alpha=1))

compareBars2(margins.prior,25*margins.post,3,c("Prior","Post"),
            main="Margins before/after Medium Trouble Shooting Task",
            sub="Observables:  cfgCor=Medium, logCor=High, logEff=Medium",
            legend.loc = "topright",
            cex.names=.75, col1=hsv(h=.1,s=.2*1:5-.1,alpha=1),
            col2=hsv(h=.6,s=.2*1:5-.1,alpha=1))

ralmond/CPTtools documentation built on Dec. 27, 2024, 7:15 a.m.