This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Final Exam Solutions General Comments: • The final was a little harder than the midterms–the median was 76, the low score was 42, and the high score was 100.5 (wow!). • I was a little disturbed at how much trouble people had with the last question as this was primarily a matter of figuring out whether your X and Y variables were categorical or quan titative and identifying the corresponding model to use. Please read the solutions to those questions carefully. • Exams will be available for pickup from the biostat department office (CHS, 5th floor 1st corridor near my office–see Helen Chien) up until April 9th and after that from me in my office. If you have questions about scoring come ask me. • Approximate grade ranges for the final exam (which are NOT the same as for the course as a whole) are given below so you have an idea how people did. If you have a question about your overall course grade send me an email. It took about 88% overall for the course to get an A and about 85% overall to get an A. Grade Score Range Number in Range A 86+ 22 A 7885.5 25 B+ 7277.5 22 B 6571.5 15 B 6064.5 6 C+ 5759.5 3 C 5356.5 2 C 4652.5 2 D/F < 46 2 THE STORY BEHIND THE EXAM: A researcher at our favorite school, the University of Calculationally Literate Adults, is interested in the factors that lead to arteriosclerosis (hardening or blockage of the arteries, often due to the buildup of fatty plaques on the artery walls.) She is also studying medications for lowering cholesterol levels since high cholesterol is a risk factor for arteriosclerosis. You will help her analyze some of her data. 1 NOTE: Unless otherwise indicated, use α = . 05 for all hypothesis tests and confidence intervals on this exam. Question 1: (35 points, 50 minutes) The researcher begins by asking whether there is a relationship between whether a person has arteriosclerosis and whether they have high cholesterol. Here high cholesterol is defined as a total cholesterol level of 250 mg/deciliter or above. She examines 25 patients with arteriosclerosis and find that 20 have high blood pressure. She also examines 25 controls who do not have arterioscle rosis and finds that 10 have high cholesterol. A contingency table analysis of her data is shown below. Use it to answer the questions on the follwing pages. . tabi 20 5\10 15, exp chi2 ++  Key    frequency   expected frequency  ++  col row  High Ch Normal Ch Total++ Arterio  20 5  25 Yes  15.0 10.0  25.0++ Arterio  10 15  25 No  15.0 10.0  25.0++ Total  30 20  50  30.0 20.0  50.0 Pearson chi2(1) = 8.3333 Pr = 0.004 Part a (2 points) Does there appear to be a statistically significant relationship between arteriosclerosis and choles terol level? Briefly explain your reasoning. (You do not need to write out all the details of the test.)terol level?...
View
Full
Document
This note was uploaded on 03/05/2008 for the course BIOSTAT 100B taught by Professor Sugar during the Winter '07 term at UCLA.
 Winter '07
 Sugar

Click to edit the document details