Skip to contents

Generate boxplots for a specified effect in a aomstats object.

Usage

# S3 method for aomstats
boxplot(
  x,
  effect,
  model,
  by = "timepoints",
  subset = NULL,
  outliers = TRUE,
  ...
)

Arguments

x

An object of class aomstats containing relational event network statistics.

effect

A string specifying the name of the effect in 'x' or an integer indicating the index of the effect to be plotted.

model

A string indicating whether the effect is in the 'sender' model or the 'receiver' model.

by

A string indicating whether the statistic is plotted across 'timepoints' (default) or 'actors'.

subset

An optional vector specifying a subset of timepoints or actors to be used for plotting. Per default, a maximum of 20 unique timepoints or actors are plotted.

outliers

A logical value specifying whether to include outliers in the plot.

...

additional arguments passed to bxp().

Details

This function produces boxplots to visually represent the distribution of a specified effect in a relational event network, as captured by a aomstats object. The 'effect' parameter allows the user to choose a specific effect for visualization, either by providing the effect's name or its index within the 'aomstats' object. The 'model' parameter indicates whether the respective effect is in the 'sender' model or the 'receiver' model. The 'by' parameter determines whether the boxplots are created across different 'timepoints' or 'actors'. At the moment, by 'actors' is only supported for the sender model. Additionally, an optional 'subset' parameter allows the user to focus on specific timepoints or actors. If 'subset' is not specified, a default maximum of 20 unique timepoints or actors are plotted. The 'outliers' argument, when set to TRUE, includes the representation of outliers in the boxplots. If set to FALSE, outliers are omitted from the visualization.

The boxplots are based on the following summary statistics of the data: The box in the middle represents the interquartile range (IQR) between the first (Q1) and third quartile (Q3), and the line inside the box represents the median. The whiskers extend from the box to the minimum and maximum values within 1.5 times the IQR below Q1 or above Q3. Outliers beyond the whiskers are plotted individually.

Examples

library(remstats)
# Load data
data(history)
# Prepare data
reh <- remify::remify(edgelist = history[,1:3], model = "actor")
# Compute effects
stats <- remstats(reh, sender_effects = ~ outdegreeSender())
# Plot the 'outdegreeSender' distribution for 20 timepoints
boxplot(stats, effect = "outdegreeSender", model = "sender")

# Plot the 'inertia' distribution for all 10 actors
boxplot(stats, effect = "outdegreeSender", model = "sender", by = "actors")