Many of the examples and exercises in the text have dealt with IQ scores. We now know that IQ scores based on the Stanford-Binet IQ test are approximately normally distributed with a mean of 100 and standard deviation 15. If you were to obtain 100 different simple random samples of size 20 from the population of all adult humans and determine 95% confidence intervals for each of them, how many of the intervals would you expect to include 100? What causes a particular interval to not include 100?