This preview shows page 1. Sign up to view the full content.
Unformatted text preview: students surveyed is small relative to the student population, and there is no response bias.) 3. Is it reasonable to assume that there is no response bias when asking students if they have ever cheated on a test? Do you think the answers will be diﬀerent if the students answer a survey online or answer questions in person to an interviewer? 4. You have a box with 400 marbles in it. Your friend draws 100 marbles from the box with replacement and ﬁnds that 20 of them are red. He calculates that a 95% conﬁdence interval for the percentage of red marbles in the box is 12% - 28%. You know that the true percentage of red marbles is 29%. What did your friend do wrong? If he did nothing wrong, how do you explain the result?...
View Full Document
This note was uploaded on 07/08/2010 for the course STATS 21 taught by Professor Ibser during the Spring '09 term at University of California, Berkeley.
- Spring '09