This preview shows pages 1–3. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.View Full Document
Unformatted text preview: Page 1 Page 2 Page 3 Page 4 Page 5 Page 6 Page 7 Total 14 Pts 12 Pts 12 Pts 16 Pts 11 Pts 19 Pts 16 Pts 100 Pts MATH 147 TEST TWO Fall 2003 October 22, 2003 Name: Section: DIRECTIONS: Show all work. Solutions with no work will receive NO credit. Neatness counts. All necessary tables are provided at the end of the test. Carry out all your calculations to at least two digits to the right of the decimal point. Part I True/False For questions 1 - 5 circle T for true and F for false. (2 points each) 1. T F Two events are independent if the occurrence of one does not change the chances for the other. 2. T F In an observational study, the regression line can be relied on for predicting the results of an intervention. 3. T F Among all lines, the one that makes the smallest r.m.s. error in predicting y from x is the Regression line. 4. T F In a regression setting for predicting y from x, the average of the residual values is 0. 5. T F If the graph of averages happens to be a straight line, then it coincides with the regression line. Part II Fill in the blank For the following questions, complete the sentence by filling in the blank. (2 points for each blank) 6. Suppose that in a certain class, there are • 70% men and 30% women; • 20% freshmen and 80% sophomores. The percentage of sophomore women in the class can be as low as . 7. Two variables have a correlation coefficient of r = 0 . 63. If each of the data items of the first variable are multiplied by 2, the resulting correlation coefficient is . 1 Part III Multiple Choice For the multiple choice questions, circle the answer which best completes the sentence or best answers the question. (3 points each) 8. In a regression setting for predicting y from x, (a) the R.M.S. error is generally smaller than the SD of y. (b) the R.M.S. error is generally smaller than the SD of x. (c) the R.M.S. error is generally larger than the SD of y. (d) the R.M.S. error is generally larger than the SD of x. (e) both (a) and (b) are true. 9. Heteroscedasticity in a regression setup (a) makes the R.M.S. error more reliable. (b) makes the prediction error more uniform. (c) means that the scatter diagram has a generally elliptical (football) shape. (d) means that the scatter diagram does not have an elliptical shape....
View Full Document
This note was uploaded on 04/09/2008 for the course MATH 147 taught by Professor Klimko during the Spring '07 term at Binghamton University.
- Spring '07