The formula for a 95% confidence interval for a mean is so well-rooted in statistical theory and practice that you might not even consider other possibilities. However, many researchers and even practitioners favor a totally different method of calculating a 95% confidence interval for the mean. It is called the bootstrap method. Starting with a sample of size n, they generate many “bootstrap samples,” calculate the sample mean of each, and report the 2.5 and 97.5 percentiles of these sample means as the endpoints of the confidence interval. Each bootstrap sample is a random sample of size n, with replacement, from the given data. That is, each member of a bootstrap sample is equally likely to be any of the original n data points. Implement this in Excel, starting with the sample of 50 salaries in the file P08_78.xlsx. Create at least 100 bootstrap samples.
Compare the resulting bootstrap confidence interval with the one from StatTools (the traditional one).