Create a violin plot

Draws a kernel density plot in combination with a boxplot in its middle. The shape of the violin is constructed using a mirrored density curve. This plot is especially designed for cases where the individual errors are zero or too small to be visualised. The idea for this plot is based on the 'volcano plot' in the ggplot2 package by Hadley Wickham and Winston Chang. The general idea for the violin plot seems to have been introduced by Hintze and Nelson (1998).

The function is passing several arguments to the functions plot, stats::density, graphics::boxplot:

Supported arguments are: xlim, main, xlab, ylab, col.violin, col.boxplot, mtext, cex, mtext

Valid summary keywords

'n', 'mean', 'median', 'sd.abs', 'sd.rel', 'se.abs', 'se.rel'. 'skewness', 'kurtosis'

Usage

plot_ViolinPlot(
  data,
  boxplot = TRUE,
  rug = TRUE,
  summary = c("n", "median"),
  summary.pos = "sub",
  na.rm = TRUE,
  ...
)

Arguments

data: numeric or RLum.Results (required): input data for plotting. Alternatively a data.frame or a matrix can be provided, but only the first column will be considered by the function
boxplot: logical (with default): enable/disable boxplot
rug: logical (with default): enable/disable rug
summary: character (with default): add statistic measures of centrality and dispersion to the plot. Can be one or more of several keywords. See details for available keywords.
summary.pos: numeric or character (with default): optional position keywords (cf. legend) for the statistical summary. Alternatively, the keyword "sub" may be specified to place the summary below the plot header. However, this latter option in only possible if mtext is not used.
na.rm: logical (with default): exclude NA values from the data set prior to any further operations.
...: further arguments and graphical parameters passed to plot.default, stats::density and boxplot. See details for further information.

Note

Although the code for this function was developed independently and just the idea for the plot was based on the 'ggplot2' package plot type 'volcano', it should be mentioned that, beyond this, two other R packages exist providing a possibility to produces this kind of plot, namely: 'vioplot' and 'violinmplot' (see references for details).

Function version

0.1.4

How to cite

Kreutzer, S., 2025. plot_ViolinPlot(): Create a violin plot. Function version 0.1.4. In: Kreutzer, S., Burow, C., Dietze, M., Fuchs, M.C., Schmidt, C., Fischer, M., Friedrich, J., Mercier, N., Philippe, A., Riedesel, S., Autzen, M., Mittelstrass, D., Gray, H.J., Galharret, J., Colombo, M., Steinbuch, L., Boer, A.d., 2025. Luminescence: Comprehensive Luminescence Dating Data Analysis. R package version 1.1.0. https://r-lum.github.io/Luminescence/

References

Daniel Adler (2005). vioplot: A violin plot is a combination of a box plot and a kernel density plot. R package version 0.2 http://CRAN.R-project.org/package=violplot

Hintze, J.L., Nelson, R.D., 1998. A Box Plot-Density Trace Synergism. The American Statistician 52, 181-184.

Raphael W. Majeed (2012). violinmplot: Combination of violin plot with mean and standard deviation. R package version 0.2.1. http://CRAN.R-project.org/package=violinmplot

Wickham. H (2009). ggplot2: elegant graphics for data analysis. Springer New York.

Author

Sebastian Kreutzer, Institute of Geography, Heidelberg University (Germany) , RLum Developer Team

Examples


## read example data set
data(ExampleData.DeValues, envir = environment())
ExampleData.DeValues <- convert_Second2Gray(ExampleData.DeValues$BT998,
                                            c(0.0438,0.0019))

## create plot straightforward
plot_ViolinPlot(data = ExampleData.DeValues)