Professional Documents
Culture Documents
Exam June Questions
Exam June Questions
SECTION A
Answer the following multiple choice questions using the Multiple Choice Answer Sheet.
Each question is worth two marks. This section is worth a total of 40 marks.
QUESTION 1
QUESTION 2
(a) land_size.
QUESTION 3
(a) positive
(b) negative
(c) zero
Page 1 of 26
QUESTION 4
QUESTION 5
Consider the regression model wage = β 0 + β 1 Age+u , where u is correlated with Age . Which
of the following assumptions is violated for sure:
QUESTION 6
Page 2 of 26
QUESTION 7
Suppose the following equation is estimated where sleep is measured in minutes and work
in hours:
If someone gets one more year of education, by how many minutes is sleep predicted to
fall?
(a) 14.8.
(b) 11.13.
(c) 29.6.
(d) 11.13%.
QUESTION 8
n=706, R2 =0.0111.
(a) 1.11%.
(b) 11.1%
(c) 11.13%.
(d) 0.1113%.
QUESTION 9
(estimate−hypothesised value)
(d)
standard error
Page 3 of 26
QUESTION 10
Consider the regression equation log(wage) = 0.284 + 0.092*educ + 0.0045 * exper. The
standard error of the educ coefficient estimate is 0.034. Assume the null hypothesis is that
the educ coefficient is equal to zero. What is the t-statistic for the educ coefficient?
(a) 0.092.
(b) 0.271.
(c) 0.370.
(d) 2.71.
QUESTION 11
(a) 0.50%.
(b) 2.5%
(c) 5%.
(d) 0.25%.
QUESTION 12
(a) 5.1%.
(b) 5.2%
(c) 0.052%.
Page 4 of 26
(d) 0.051%.
Page 5 of 26
QUESTION 13
Consider a regression model where the estimation results give the p-value of a coefficient as
“0.701”. At what levels of significance is this coefficient statistically significantly different from
zero?
(a) 1%.
QUESTION 14
Note that salesl2 = sales*sales. What is the effect of an increase from 2 to 3 in sales on
CEOSAL?
(a) 0.30
(b) 0.45
(c) 0.41
(c) 0.29
QUESTION 15
(a) 11.25
(b) 0.009
(c) 5.625
Page 6 of 26
(d) 0.018
Page 7 of 26
QUESTION 16
QUESTION 17
(a) 1.2
(b) 1.4
(c) 2.1
(d) 1.6
QUESTION 18
Page 8 of 26
QUESTION 19
(a) standard errors are valid, whereas the t statistics are invalid.
(b) t statistics are valid, but the standard errors are invalid.
QUESTION 20
Page 9 of 26
SECTION B
This section comprises three short-answer questions related to the STATA output shown
below. Students must answer all three questions in the script book provided. This section is
worth a total of 10 marks.
Page 10 of 26
QUESTION 1
In the STATA output above, lwage is the log of monthly earnings, educ is education in years,
exper is experience in years and educexper = educ*exper, the interaction of education and
experience. What is the predicted effect of 1 more year of education on wages when
educ=10 and exper=10? What is the predicted effect of 1 more year of education on wages
when educ=20 and exper=20?
(6 marks)
QUESTION 2
Using the STATA output above, interpret the meaning of the R-squared.
(2 marks)
QUESTION 3
Using the STATA output above, test the hypothesis that the coefficient on educ is different
from zero at the 1% level. Conduct a one-sided test. Use the critical value approach.
(2 marks)
Page 11 of 26
FORMULA SHEET
estimate−hypothesised value
t=
standard error
Logarithmic/Quadratic/Interaction specifications
For the model log ( y )= β^ 0 + ^β 1 x 1 + ^β 2 x 2, the exact effect of a change in explanatory variable x2
is:
[
% ∆ ^y =100 exp ( ^β 2 ∆ x 2 )−1 ]
Page 12 of 26
∆ ^y ^ ^
The approximation of the marginal effect of x1 on y is given by: ≈ β +β x
∆ x1 1 2 2
Page 13 of 26