plot.xbal {RItools}R Documentation

Plotting xBalance Objects

Description

A plot method for xBalance objects. WORK IN PROGRESS. PATCHES AND CODE SUGGESTIONS APPRECIATED.

We aim this plot to be a diagnostic tool rather than a publication quality presentation tool.

Usage

## S3 method for class 'xbal':
plot(x,adjustxaxis=.25,segments=TRUE,legend=TRUE,
                    mar=c(3,3,2,0)+0.1,mgp=c(1.5,.5,0),tck=-.01,
                    which.strata=dimnames(x$results)[["strata"]],thestratalabs=which.strata,
                    which.stats="std.diff", ##dimnames(x$results)[["stat"]],
                    which.vars=dimnames(x$results)[["vars"]],thevarlabs=which.vars,
                    thexlab="Standardized Differences",
                    thecols=rainbow(length(which.strata)),
                    thesymbols=c(19,22,23,24,25)[1:length(which.strata)],...)

Arguments

x An object of class "xbal" — the result of a call to xBalance()
adjustxaxis amount by which the x-axis should be expanded.
segments Should thin horizontal lines be plotted connecting the statistics for the different stratifications.
legend Should a legend be plotted?
mar Preliminary margin setting
mgp Preliminary setting for axis labels
tck Length of the tick marks
which.strata The stratification candidates to include in the printout. Default is all.
thestratalabs The text labels for the strata.
which.stats a character vector of length 1. The test statistics to include. Default is the standardized difference.
which.vars The variables for which test information should be displayed. Default is all.
thevarlabs The text labels for the variables.
thexlab The label for the x-axis (should tell viewers about the statistic chosen).
thecols A vector of colors either (a) one per strata or (b) one for all strata.
thesymbols A vector of plotting symbols either (a) one per strata or (b) one for all strata.
... other arguments to the plot.default function setting up the plotting region.

Value

The plot allows a quick visual comparison of the effect of different stratification designs on the comparability of different variables. This is not a replacement for the omnibus statistical test reported as part of print.xbal. But, it does allow the analyst an easy look at which variables might be the primary culprits of overall imbalances and/or a way to assess whether certain important covariates might be imbalanced even if the omnibus test reports that the stratification overall produces balance.

References

xBalance

Examples

data(nuclearplants)

xb0<-xBalance(pr~ date + t1 + t2 + cap + ne + ct + bw + cum.n,data=nuclearplants)

plot(xb0)

xb1<-xBalance(pr~ date + t1 + t2 + cap + ne + ct + bw + cum.n,
         strata=data.frame(unstrat=factor(character(32)),
           pt=factor(nuclearplants$pt)),
         data=nuclearplants,
         report=c("adj.means","adj.mean.diffs","std.diffs", "z.scores", "chisquare.test","p.values"))

plot(xb1)


[Package RItools version 0.1-5 Index]