inset: An EDA Graphical and Statistical Summary

In rgr: Applied Geochemistry EDA

Description

Plots a three panel graphical distributional summary for a data set, comprising a histogram and a cumulative normal percentage probability (CPP) plot, together with a table of selected percentiles of the data and summary statistics between them. Optionally the EDA graphics may be plotted with base 10 logarithmic scaling.

Usage

inset(xx, xlab = deparse(substitute(xx)), log = FALSE, xlim = NULL, 
	nclass = NULL, colr = NULL, ifnright = TRUE, table.cex = 0.7, ...)

Arguments

xx	name of the variable to be plotted.
xlab	by default the character string for xx is used for the x-axis plot titles. An alternate title can be displayed with xlab = "text string", see Examples.
log	to display the data with logarithmic (x-axis) scaling, set log = TRUE.
xlim	default limits of the x-axis are determined in the function. However when used stand-alone the limits may be user-defined by setting xlim, see Note below.
nclass	the default procedure for preparing the histogram depends on sample size. Where N <= 500 the Scott (1979) rule is used, and when N > 500 the Freedman-Diaconis (1981) rule; both these rules are resistant to the presence of outliers, and usually provide informative histograms. Alternately, the user may define the histogram binning by setting nclass, i.e. nclass = "scott", nclass = "fd" or nclass = "sturges"; the latter being designed for normal distributions (Scott, 1992). See Venables and Ripley (2001) for details.
colr	by default the histogram is infilled in grey, colr = 8. If no infill is required, set colr = 0. See function display.lty for the range of available colours.
ifnright	controls where the sample size is plotted in the histogram display, by default this in the upper right corner of the plot. If the data distribution is such that the upper left corner would be preferable, set ifnright = FALSE. If neither option generates an acceptable plot, setting ifnright = NULL suppresses the display of the data set size.
table.cex	controls the size of the text in the central panel of summary statistics table, the default is table.cex = 0.7, which has been found to be optimal. If the entire table does not display, just parts of the columns, see Note below.
...	further arguments to be passed to methods. For example, by default individual data points in the CPP plot are marked by a plus sign, pch = 3, if a cross or open circle is desired, then set pch = 4 or pch = 1, respectively. See display.marks for all available symbols. Adding ifqs = TRUE results in horizontal and vertical dotted lines being plotted at the three central quartiles and their values, respectively, in the CPP plot.

Details

A histogram is displayed on the left, and a cumulative normal percentage probability plot on the right. Between the two is a table of simple summary statistics, computed by gx.stats, including minimum, maximum and percentile values, robust estimates of standard deviation, and the mean, standard deviation and coefficient of variation. The plots may be displayed with logarithmic axes, however, the summary statistics are not computed with a logarithmic transform.

Note

Sometimes the table between the two plots may be left and/or right truncated, or incompletely displayed. Reducing the size of the graphics window will lead to a complete display. If this needs to be done the function needs to be repeated to ensure a correctly dimensioned display is saved. Once as a complete saved graphics file the image may be resized in the receiving document.

Any less than detection limit values represented by negative values, or zeros or other numeric codes representing blanks in the data, must be removed prior to executing this function, see ltdl.fix.df.

Any NAs in the data vector are removed prior to displaying the plot.

If the default selection for xlim is inappropriate it can be set, e.g., xlim = c(0, 200) or c(2, 200). If the defined limits lie within the observed data range a truncated plot will be displayed. If this occurs the number of data points omitted is displayed below the total number of observations.

The purpose of this function is to prepare publication quality graphics (.emf or .ps) files that can be included in reports or used as inset statistical summaries for maps. If a series of these are to be prepared the function inset.exporter can be used to advantage as it saves a graphics file as part of its procedure.

For summary statistics tables to complement the graphical display see, gx.stats, gx.summary1, gx.summary2 and gx.ngr.summary.

In some R installations the generation of multi-panel displays and the use of function eqscplot from package MASS causes warning messages related to graphics parameters to be displayed on the current device. These may be suppressed by entering options(warn = -1) on the R command line, or that line may be included in a ‘first’ function prepared by the user that loads the ‘rgr’ package, etc.

Author(s)

Robert G. Garrett

References

Venables, W.N. and Ripley, B.D., 2001. Modern Applied Statistsis with S-Plus, 3rd Edition, Springer, 501 p. See pp. 119 for a description of histogram bin selection computations.

See Also

gx.hist, cnpplt, gx.stats, inset.exporter, ltdl.fix.df, remove.na

Examples

## Make test data available
data(kola.o)
attach(kola.o)

## Generates an initial display
inset(Cu)

## Provides a more appropriate display for pubication
inset(Cu, xlab = "Cu (mg/kg) in <2 mm O-horizon soil", log = TRUE)

## NOTE: The example statistics table may not display correctly

## Detach test data
detach(kola.o)

Example output

Loading required package: MASS
Loading required package: fastICA
Warning messages:
1: In par(old.par) : graphical parameter "cin" cannot be set
2: In par(old.par) : graphical parameter "cra" cannot be set
3: In par(old.par) : graphical parameter "csi" cannot be set
4: In par(old.par) : graphical parameter "cxy" cannot be set
5: In par(old.par) : graphical parameter "din" cannot be set
6: In par(old.par) : graphical parameter "page" cannot be set
Warning messages:
1: In par(old.par) : graphical parameter "cin" cannot be set
2: In par(old.par) : graphical parameter "cra" cannot be set
3: In par(old.par) : graphical parameter "csi" cannot be set
4: In par(old.par) : graphical parameter "cxy" cannot be set
5: In par(old.par) : graphical parameter "din" cannot be set
6: In par(old.par) : graphical parameter "page" cannot be set

rgr documentation built on May 2, 2019, 6:09 a.m.