In trying to find out what freshmen think about the food served on campus, campus-caterer has considered both an SRS and a stratified sample. Now they have run into a problem:
it is simply too difficult and time consuming to track down the individuals whose names were chosen for their sample. Fortunately freshmen at the college is housed in 10 freshmen dorms. How could you use these facts to draw a cluster sample? how might that alleviate the problem?what concerns do you have?