This preview shows pages 1–4. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Name: ID number: Put all materials away and turn off your cell phone ringer. You have 120 minutes for the test. It has (?) pages, including this page, and (?) possible points. Check to be sure that your test is complete. Read through all the problems and decide how much time to allocate to each one. You must SHOW YOUR WORK to get partial credit. 1 Problem 1 (40 points total, 4 points each) Circle one of the listed choices for each question (no explanation is needed). 1. In a regression problem where serial correlation exists, which major assumption has been violated? (b) (a) Linearity (b) Independence (c) Normality (d) Constant variance 2. If serial correlation is positive ( r 1 > 0), then the adjustment for serial correlation will make standard errors (a) (a) larger. (b) smaller. (c) Cant tell without seeing the data. 3. For a chisquared test for independence, based on a table with 3 rows and 4 columns, the degrees of freedom for the 2 test statistic will be (d) (a) 12 (b) 9 (c) 8 (d) 6 4. For a 2 2 table of counts, where neither variable is treated as a response, which hypothesis is more appropriate? (b) (a) Hypothesis of homogeneity. (b) Hypothesis of independence. 5. In a study, a sample of iPhone users was obtained from a list of all iPhone users, and a sample of Android users was obtained from a list of all Android users. Both samples were asked whether they were satisfied with their smartphones. This is an example of (b) (a) Poisson sampling. (b) prospective product binomial sampling. (c) retrospective product binomial sampling. (d) a randomized binomial experiment. 2 6. For the study described in the previous question, are we able to estimate the population proportion of iPhone users? (b) (a) Yes. (b) No. Consider the following table of counts for 7 & 8: Response Yes No Explanatory Group 1 21 3 Group 2 14 10 7. Is the Normal approximation for 1 2 appropriate? (a) (a) Yes. (b) No. 8. What is the estimated odds ratio, = 1 / 2 ? (c) (a) 0.2917 (b) 0.20 (c) 5 9. True or False: the logistic regression model assumes constant variance. (b) (a) True....
View
Full
Document
This note was uploaded on 01/22/2012 for the course STAT 3022 taught by Professor Staff during the Fall '08 term at Minnesota.
 Fall '08
 Staff

Click to edit the document details