Thursday, January 5, 2012
Do you think that 100 people was a good number to conduct a study on and could you explain your answer?
It depends. There are ways to formally calculate how well your sample represents the total population but it requires some umptions. If you get survey results from 100 people (randomly selected) and they are 100 of the 200 people total who have ever had some specific thing happen to them, the results should be pretty descriptive. If you sample 100 people who happen to own sailboats over 100 feet long and who happen to live in Hawaii, the results probably do not provide much help if you are interested in understanding Walmart employees.
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment