Read more about Data Workbench’s End-of-life announcement.
Defining dependent correlation points that make sense in your market is the essence of correlation analysis.
These use cases highlight the art of identifying relationships as correlation points applied to the science of the Pearson correlation coefficient.
Digital publishers want to maximize their understanding of the potential relationship between social media activity and visits to their website. For example, the digital publisher runs the correlation report between hourly Twitter mentions and visits for a two week period. The correlation is found to be r = 0.28, which indicates a medium, positive relationship between Twitter mentions and website visits.
E-retailers are interested in driving increased revenue. For example, an e-retailer wants to compare a number of secondary success events (e.g., file downloads, product detail page views, internal search click-throughs, etc.) with weekly web revenue. They can quickly identify internal search click-throughs as having the highest correlation (r = 0.46), which may indicate an area for optimization.