Mann-Whitney U power assessment
A power analysis allows for the likelihood of an error to be determined. Though the appropriate sample can be gathered and a test may be significant, a power analysis is needed to determine the confidence that can be given to the test results. Assess the Mann-Whitney U test power analysis provided for the likelihood of a Type II error in rejecting the null hypothesis, there is no difference in the number of rounds played in the two versions.
Recall the Mann-Whitney U test assessed the median number of rounds subjects played of a video game, detecting a difference in the two version groups.
This exercise is part of the course
A/B Testing in R
Exercise instructions
- Determine the probability of a Type II error if the null hypothesis was rejected given our previous power analysis result of
.1138
.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Determine the probability of a Type II error
type_II_error = ___
print(paste0("The probability of a Type II Error is: ", type_II_error))