Simpson's paradox, or the Yule-Simpson effect, is a phenomenon in probability and statistics, in which a trend appears in several different groups of data but disappears or reverses when these groups are combined.
simulate_simpson(n = 100, r = 0.5, groups = 3, difference = 1)
n | The number of observations for each group to be generated. |
---|---|
r | A value or vector corresponding to the desired correlation coefficients. |
groups | Number of groups. |
difference | Difference between groups. |
A dataset.
data <- simulate_simpson(n = 100, groups = 5, r = 0.5) library(ggplot2) ggplot(data, aes(x = V1, y = V2)) + geom_point(aes(color = Group)) + geom_smooth(aes(color = Group), method = "lm") + geom_smooth(method = "lm")#>#>