midterm+1+answers - Department of Economics University of...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Department of Economics Fall 2007 University of California Prof. Woroch Economics 140 : MIDTERM #1 ANSWERS I. SHORT QUESTIONS : Give a concise but complete answer to each of the following 3 questions. Each question is worth 15 points for a total of 45. 1. You were interested in the relationship between the alcohol consumption by college students and their academic performance. To your surprise, the University provides you with the results of a survey it conducted in which 500 undergraduates reported the average number of drinks they consume per week, matched with the registrar’s records of students’ Grade Point Average at the time of the survey. You estimate the bivariate linear regression of student GPA on their alcohol consumption. (a) Give reasons why Least Squares Assumption #1 may not hold for your regression. (b) Discuss how, if given unlimited powers by the University, you would have collected these student data to better ensure that Assumption #2 would hold. Answer : (a) It is likely that other determinants of academic performance are left out of the regression that are, in addition, correlated with alcohol consumption. E.g., personal and family stress could lead to alcohol consumption and could independently reduce academic performance. Alcohol use may be a complement or substitute for drug use which likely will reduce performance. One other possibility could occur if the departure of reported alcohol consumption varies with true alcohol consumption, as when heavy (light) drinkers under (over) report the amount. (b) You would like to randomly draw an undergrad from the student body and then randomly select an amount of weekly alcohol consumption and force them to drink that amount, no more and no less. You would then record their GPA over the period of this consumption, especially their GPA at the end of this period. You would not allow any deviation from the consumption such as reporting they had consumes the assigned amount when they had consumed more. 2. The R 2 produced by a regression of public high school seniors’ SAT scores on the per-student expenditure in each school district is much higher in California than in New York. (a) Give reasons why the two R 2 ’s might differ. (b) Would you conclude that expenditures cause SAT scores in California but not in New York?
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 10/21/2008 for the course ECON 140 taught by Professor Duncan during the Fall '08 term at University of California, Berkeley.

Page1 / 4

midterm+1+answers - Department of Economics University of...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online