plot.data_descr() R function from [MSmix]

Plot descriptive statistics for partial rankings

plot method for class "data_descr".


## S3 method for class 'data_descr'
plot(
  x,
  cex_text_mean = 1,
  cex_symb_mean = 12,
  marg_by = "item",
  cex_text_pc = 3,
  cex_range_pc = c(8, 20),
  ...
)

Arguments

x: An object of class "data_descr" returned by data_description.
cex_text_mean: Positive scalar: the magnification to be used for all the labels in the plot for the mean rank vector. Defaults to 1.
cex_symb_mean: Positive scalar: the magnification to be used for the symbols in the pictogram of the mean rank vector. Defaults to 12.
marg_by: Character indicating whether the marginal distributions must be reported by "item" or by "rank" in the heatmap. Defaults to "item".
cex_text_pc: Positive scalar: the magnification to be used for all the labels in the bubble plot of the paired comparison frequencies. Defaults to 3.
cex_range_pc: Numeric vector indicating the range of values to be used on each axis in the bubble plot of the paired comparison frequencies. Defaults to c(8,20).
...: Further arguments passed to or from other methods (not used).

Returns

A list of 5 labelled plots displaying descriptive summaries of the partial ranking dataset, namely: i) n_ranked_distr: a barplot of the frequency distribution (%) of the number of items actually ranked in each partial sequence, ii) picto_mean_rank: a basic pictogram of the mean rank vector, iii) marginals: a heatmap of the marginal distributions (either by item or by rank), iv) ecdf: the ecdf of the marginal rank distributions and v) pc: a bubble plot of the pairwise comparison matrix.

Details

The plots of the marginals distributions and pairwise comparisons are constructed if the object x was obtained from the data_description routine with arguments marg = TRUE and pc = TRUE; otherwise, a NULL element in the output list is returned.

Examples


## Example 1. Plot the mean rank vector and marginal distributions for the Antifragility dataset.
r_antifrag <- ranks_antifragility[, 1:7]
desc <- data_description(r_antifrag)
p_desc <- plot(desc)
p_desc$picto_mean_rank()
p_desc$marginals()

## Example 2. Plot the distribution of the number of ranked items and the
# pairwise comparison matrix for the Sports dataset.
r_sports <- ranks_sports[, 1:8]
desc <- data_description(rankings = r_sports, borda_ord = TRUE)
p_desc <- plot(desc, cex_text_mean = 1.2)
p_desc$n_ranked_distr()
p_desc$pc()

## Example 3. Plot the ecdf's for the marginal rank distributions for the Sports dataset by gender.
r_sports <- ranks_sports[, 1:8]
desc_f <- data_description(rankings = r_sports, subset = (ranks_sports$Gender == "Female"))
p_desc_f <- plot(desc_f, cex_text_mean = 1.2)
p_desc_f$ecdf()
desc_m <- data_description(rankings = r_sports, subset = (ranks_sports$Gender == "Male"))
p_desc_m <- plot(desc_m, cex_text_mean = 1.2)
p_desc_m$ecdf()

References

Wickham H (2016). ggplot2: Elegant Graphics for Data Analysis. Springer-Verlag New York. ISBN 978-3-319-24277-4, https://ggplot2.tidyverse.org.

plot.data_descr function