The data for this exercise derive from a sample of 5,000 visits to amazon.com, and, as in the example in this chapter, the data for each visit list the host that linked to Amazon. The key difference from the example in the chapter is that these data are from the fall of 2014. The data omit sessions that did not come from a host (i.e., were directly typed). In 2014, about 60% of visits did not use a host.

Compare the hosts found in these data to those that are summarized in the example of this chapter. What important similarities and differences do you find, and explain briefly why you think these aspects of the comparison are important. Structure your answer using the 4M paradigm, starting with a motivating question that you plan to answer, followed by your choice of approach, the mechanics, and then a concluding message.