3.2 Graphical Measures
3.2.1 Shape
Properly labeling your graphs is essential to ensure that viewers can easily understand the data presented. Below are several examples of graphical measures used to assess the shape of a dataset.
# Generate random data for demonstration purposes
data <- rnorm(100)
# Histogram: A graphical representation of the distribution of a dataset.
hist(
data,
labels = TRUE,
col = "grey",
breaks = 12,
main = "Histogram of Random Data",
xlab = "Value",
ylab = "Frequency"
)
# Interactive Histogram: Using 'highcharter' for a more interactive visualization.
# pacman::p_load("highcharter")
# hchart(data, type = "column", name = "Random Data Distribution")
# Box-and-Whisker Plot: Useful for visualizing the distribution and identifying outliers.
boxplot(
count ~ spray,
data = InsectSprays,
col = "lightgray",
main = "Boxplot of Insect Sprays",
xlab = "Spray Type",
ylab = "Count"
)
# Notched Boxplot: The notches indicate a confidence interval around the median.
boxplot(
len ~ supp * dose,
data = ToothGrowth,
notch = TRUE,
col = c("gold", "darkgreen"),
main = "Tooth Growth by Supplement and Dose",
xlab = "Supplement and Dose",
ylab = "Length"
)
# If the notches of two boxes do not overlap, this suggests that the medians differ significantly.
# Stem-and-Leaf Plot: Provides a quick way to visualize the distribution of data.
stem(data)
#>
#> The decimal point is at the |
#>
#> -2 | 4321000
#> -1 | 87665
#> -1 | 44433222111000
#> -0 | 998888886666665555
#> -0 | 433322221100
#> 0 | 0112233333344
#> 0 | 5666677888999999
#> 1 | 0111122344
#> 1 | 699
#> 2 | 34
# Bagplot - A 2D Boxplot Extension: Visualizes the spread and identifies outliers in two-dimensional data.
pacman::p_load(aplpack)
attach(mtcars)
bagplot(wt,
mpg,
xlab = "Car Weight",
ylab = "Miles Per Gallon",
main = "Bagplot of Car Weight vs. Miles Per Gallon")
Below are some advanced plot types that can provide deeper insights into data:
# boxplot.matrix(): Creates boxplots for each column in a matrix. Useful for comparing multiple variables.
graphics::boxplot.matrix(
cbind(
Uni05 = (1:100) / 21,
Norm = rnorm(100),
T5 = rt(100, df = 5),
Gam2 = rgamma(100, shape = 2)
),
main = "Boxplot Marix",
notch = TRUE,
col = 1:4
)
# Violin Plot (vioplot()): Combines a boxplot with a density plot, providing more information about the distribution.
library("vioplot")
vioplot(data, col = "lightblue", main = "Violin Plot Example")
3.2.2 Scatterplot
Scatterplots are useful for visualizing relationships between two continuous variables. They help identify patterns, correlations, and outliers.
Pairwise Scatterplots: Visualizes relationships between all pairs of variables in a dataset. This is especially useful for exploring potential correlations.
