Serge was curious if a sample third quartile was an unbiased estimator of a population third quartile. He started with a large normally distributed population of test scores whose third quartile was Q3=80 points. He then took a random sample of 6 tests and calculated the third quartile of the sample. He replaced those tests and repeated this process for a total of 40 trials. His results are summarized in the dot plot below, where each dot represents the third quartile from a sample of 6 tests.