Mann-Whitney U analysis
A Mann-Whitney U test is a non-parametric assessment of the median of two groups, making no assumption about the distribution. A Mann-Whitney U test can be assessed by finding the rank-biserial r effect size and running a power analysis on the resulting values.
A dataset of subjects playing a video game includes a column indicating the number of rounds of the game they have played and two versions of the game which each subject participated in one of. You are interested in whether there are a different number of rounds played in the two versions. The distributions are not normal, indicating the Mann-Whitney U test should be used to assess the group differences.
The gamedata
dataset, as well as the pwr
and effectsize
packages have been loaded for you.
This exercise is part of the course
A/B Testing in R
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Run the Mann-Whitney U test
wilcox.test(___)