Creating bar plots for A/B design
Clear data visualization is critical to easily and thoroughly representing analysis results to publication readers or presentation audiences. Bar plots are common and easy for an audience of any background to assess but require extra data preparation to include error bars.
A company has the A/B test design data from users that have visited their website. The company is interested in if users who clicked on their new website ad spent more. Create a bar plot to present the test results in an easy-to-understand manner to the company's board.
The dplyr and ggplot2 packages have been loaded for you, in addition to the webdata data in long format, which is reduced to only the Click and AmountSpent columns. The groups are in the Click column.
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.
# Prepare the data
AdData <- ___ %>%
group_by(___) %>%
___(AvgSpent = ___, SdSpent = ___)