New Statistics two samples (idependent & dependent)

Source: R/NewStats_2samples.R

It plots the two samples and the difference between them with their confidence intervals (CI), based on the two samples being independent or dependent.

NewStats_2samples(
  x,
  y,
  dep = FALSE,
  conf.level = 0.95,
  col.x = "blue",
  col.y = "green3",
  col.diff = "red",
  ylab.diff = "Difference"
)

Arguments

x

Sample 1
y

Sample 2
dep

Logical indicating if the samples are dependent (Default is F)
conf.level

Confidence level for the interval (Default is 0.95)
col.x

Color to use for sample 1
col.y

Color to use for sample 2
col.diff

Color to use for the difference
ylab.diff

Label for the secondary y-axis for the difference

Value

A ggplot object

Details

The labels of the plot are generic but they can be customised using the labs() and scale_x_discrete(labels = c()) functions. For the dependent samples case the two means are joined by a line, to indicate the dependency

References

Cumming, G. (2014). The New Statistics: Why and How - Psychological Science, 25(1): 7-29.

Examples

set.seed(101)
x = rnorm(20, 15, 7)
y = rnorm(20, 10, 5)
y1 = rnorm(20,x/1.1,2)
NewStats_2samples(x, y, dep = FALSE)

NewStats_2samples(x, y1, dep = TRUE)