Read FAQ 8.1.1 and then reconsider Exercise 8.1.29 based on Exploration 8.1, where you investigated whether there was evidence of an association between the type of default option and whether a person chooses to be an organ donor.
a. What would be a danger of conducting three separate tests, comparing two groups at a time rather than one overall test?
b. In Exploration 8.1 you should have found strong evidence of an association between the type of default option and whether a person chooses to be an organ donor. Now to conduct follow-up tests, suppose that we wanted to control the family wise error rate at 5%. Would the adjusted Type I error rate for any one of the three tests be larger than, smaller than, or the same as 5%?