car (version 2.1-6)

Boxplot: Boxplots With Point Identification

Description

Boxplot is a wrapper for the standard R boxplot function, providing point identification, axis labels, and a formula interface for boxplots without a grouping variable.

Usage

Boxplot(y, ...)
# S3 method for default
Boxplot(y, g, labels, id.method = c("y", "identify", "none"), 
    id.n=10, xlab, ylab, ...)
# S3 method for formula
Boxplot(formula, data = NULL, subset, na.action = NULL, labels., 
    id.method = c("y", "identify", "none"), xlab, ylab, ...)
# S3 method for list
Boxplot(y, xlab="", ylab="", ...)
# S3 method for data.frame
Boxplot(y, labels=rownames(y), ...)
# S3 method for matrix
Boxplot(y, ...)

Arguments

y

a numeric variable for which the boxplot is to be constructed; a list of numeric variables, each element of which will be treated as a group; a numeric data frame or a numeric matrix, each of whose columns will be treated as a group.

g

a grouping variable, usually a factor, for constructing parallel boxplots.

labels, labels.

point labels; if not specified, Boxplot will use the row names of the data argument, if one is given, or observation numbers, or row names if y is a data frame or matrix (that has row names).

id.method

if "y" (the default), all outlying points are labeled; if "identify", points may be labeled interactive; if "none", no point identification is performed.

id.n

up to id.n high outliers and low outliers will be identified in each group, (default, 10).

xlab, ylab

text labels for the horizontal and vertical axes; if missing, Boxplot will use the variable names, or, in the case of a list, data frame, or matrix, empty labels.

formula

a `model' formula, of the form ~ y to produce a boxplot for the variable y, or of the form y ~ g, y ~ g1*g2*..., or y ~ g1 + g2 + ... to produce parallel boxplots for y within levels of the grouping variable(s) g, etc., usually factors.

data, subset, na.action

as for statistical modeling functions (see, e.g., lm).

…

further arguments, such as at, to be passed to boxplot.

References

Fox, J. and Weisberg, S. (2011) An R Companion to Applied Regression, Second Edition, Sage.

See Also

boxplot

Examples

# NOT RUN {
Boxplot(~income, data=Prestige, id.n=Inf) # identify all outliers
Boxplot(income ~ type, data=Prestige)
Boxplot(income ~ type, data=Prestige, at=c(1, 3, 2))
Boxplot(k5 + k618 ~ lfp*wc, data=Mroz)
with(Prestige, Boxplot(income, labels=rownames(Prestige)))
with(Prestige, Boxplot(income, type, labels=rownames(Prestige)))
Boxplot(scale(Prestige[, 1:4]))
# }