Question

PART 1

You are studying the following regression on earnings of a CEO:   

Earnings)= 3.86 - 0.28Female + 0.37MarketValue + 0.004Return

You wonder whether any of the independant variables should be introduced in the model in a nonlinear fashion instead. Right now, they are all present in their original form. Which variables must you test to see if a nonlinear version of them is better suited?

       
A. Earnings, Female, MarketValue, Returns

       
B. Earnings, MarketValue, Returns

       
C. Female, MarketValue, Return

       
D. MarketValue, Returns

PART 2

"A standard ""money demand"" function used by macroeconomists has the form ln(m) = Beta0 + Beta1 ln(GDP) + Beta2 R, Where m is the quantity of (real) money, GDP is the value of (real) gross domestic product, and R is the value of the nominal interest rate measured in percent per year. Supposed that Beta 1 = 1.05 and Beta 2 = -0.03. What is the expected change in m if the interest rate increases from 5% to 9%? Round to nearest integer"

       
A. decrease 12%

       
B. decrease 9%

       
C. increase 12%

       
D. "decrease $7,387"

PART 3

"This problem is inspired by a study of the ""gender gap"" in earnings in top corporate jobs [Bertrand and Hallock (2001)]. The study compares total compensation among top executives in a large set of U.S. public corporations in the 1990s. (Each year these publicly traded corporations must report total compensation levels for their top five executives.) Let Female be an indicator variable that is equal to 1 for females and 0 for males. A regression of the logarithm of earnings onto Female yields ln(Earnings) = 6.55 -0.41Female, SER = 2.44. The Standard Errors for the Constant is (0.01) and for the Female variable is (0.05). The SER tells us all of the following, except:"

       
A. The Standard Error of the regression

       
B. The % of the variance in Earnings we have explained

       
C. The standard deviation of the regression error

       
D. The square root of the variance of the residuals

PART 4

"Assume that you had estimated the following quadratic regression model: Test Score = 607.3 + 3.85Income - 0.0423Income². If income is in thousands, please interpret the coefficient on the Income² term:"

      
A. Cannot interpret that coefficient alone

       
B. A 1 unit increase in income is associated with a 0.0423 points decrease in TestScores

       
C. "A $1,000 increase in income is associated with a 0.0423 points decrease in TestScores"

       
D. "A $1,000 increase in income is associated with a 4.23 % decrease in TestScores"

Answer 1

Answer 1:

Option D. In order to test the non-linear version of the above model, market values and returns should be used. Market values and returns are non linear because there can be exponential changes in market values and returns for which a non-linear version of the model is best suited.

Answer 2:

option A. A 1 per cent increase in the rate of interest, reduces money demand by 3 per cent. Thus,a decrease of 4 per cent in the rate of interest will reduce money demand by 3 * 4=12 per cent.

Answer 3:

Option D.The SER depicts the standard error of regression, the percentage of the variance in the earnings that we have explained. It does not depict the square root of the variance of the residuals.

Answer 4:

Option C.  "A $1,000 increase in income is associated with a 0.0423 points decrease in TestScores". This is because income is in thousands and the coefficient of income is 0.0423.