Adam Smith Business School

Subject of Economics
Degree of MSc
Degree Exam
Basic Econometrics, ECON5002
Friday, 20 December 2019, 09:30-11:30

Please ensure that you write the course code (as above), your student ID, date of birth
and the number of the question that you have attempted on each answer sheet.

How to complete this exam:

• Students should answer ONE question from Section A and ONE question from
Section B.

Materials supplied:
• Tables

Materials allowed:
• Calculators: Casio FX-83GT/Casio-83GT+, Casio FX-85GT/Casio FX-85GT+, Sharp
EL531WH, Aurora AX-582BL, Sharp EL-233SBBK/Sharp ELSI MATE EL-233S

Instructions to students:
• Both entry and exit to the examination hall will be at the absolute discretion of the
invigilator.
• No candidate will be permitted to leave within the first hour or the last half hour of this
exam.

Using exam answer sheets

•
•

• Always use a black pen.

• Complete personal information on all white sheets supplied before the exam begins.
• Use the standard character set, printed above, when hand writing in data boxes. E.g.
Student ID, Date of Birth, Question Number. Keep your characters inside the boxes.
• Use one white written answer sheet per question, using BOTH sides if required.
• For this exam, the required number of white answer sheets is TWO.
• Request yellow continuation sheets to continue writing answer if there is not enough
space on the white sheet.
• You must return all answer sheets to the invigilator even if you have not attempted all
questions.

1 Continued Overleaf
This page has been left blank for student notes – anything written here will not be marked.

2 Continued Overleaf
Section A
You must answer ONE questions in this section.
Please use ONE WHITE answer sheet per question. If there is not enough
space on a white sheet, please raise your hand to request a YELLOW answer
sheet in order to continue your answer.

1. Consider the simple regression with a constant

Yi = α + βXi + ui , i = 1, . . . , n. (1)

1.1. Verify the following numerical properties for the OLS estimator:
n
X n
X n
X n
X
(i) ûi = 0, (ii) ûi Ŷi = 0, (iii) Ŷi = Yi (2)
i=1 i=1 i=1 i=1

where ûi = Yi − Ŷi , Ŷi = α̂ + β̂Xi , and α̂ and β̂ denote the OLS estimators of α and
β, respectively. Show your calculations. [10%]
1.2. Set β = 0 in model (1), that is, consider the model

Yi = α + ui , i = 1, . . . , n. (3)

Assume that ui ∼ i.i.d.(0, σ 2 ), that is, the errors ui are independent and identically
distributed across i, with mean 2
−1
Pnzero and variance σ . Show that2 the OLS estimator
of α, α̂, is equal to Ȳ = n i=1 Yi and the variance of α̂ is σ /n. [15%]
1.3. Verify which of the numerical properties described in display (2) hold for the OLS
estimator of model (3). Show your calculations. [15%]

2. There are different ways to combine features of the Breush-Pagan and White tests for
heteroskedasticity. One possibility is to run the “hybrid” regression below

û2i on xi1 , xi2 , . . . , xik , ŷi2 , for i = 1, . . . , n (4)

where the ûi are the OLS residuals and the ŷi are the OLS fitted values of a regression
of yi on xi1 , xi2 , . . . , xik . Of course, we always include an intercept in the regressions.
2.1. How would you test for heteroskedasticity in regression (4)? Please specify which
test would you use and the associated degrees of freedom. [10%]

2.2. Explain why the R2 of the regression above will always be at least as large as the
R2 of the regression in the Breush-Pagan test. [10%]

3 Continued Overleaf
 2.3. Does the previous part imply that the new test always delivers a smaller p−value
than the Breush-Pagan test? Explain. [10%]
2.4. Suppose some suggest also adding ŷi to the newly proposed test. What do you
think of this idea? Explain. [10%]

Section B
You must answer ONE questions in this section.
Please use ONE WHITE answer sheet per question. If there is not enough
space on a white sheet, please raise your hand to request a YELLOW answer
sheet in order to continue your answer.

3. It is widely documented that there is a gender gap in earnings in top corporate jobs.
Consider the following result from a study that compares earnings among top executives
in a large set of big U.S. public companies:
\
ln(Earnings) = 6.48 − 0.44 F emale, SSR = 2.65 (5)
(0.01) (0.05)

where the natural logarithm of earnings is regressed on F emale which is an indicator

variable that is equal to 1 for females and 0 for males. The numbers in parentheses are
the standard errors, and SSR denotes the sum of squared residuals.
3.1. Interpret all the estimated coefficients and the value of SSR. Test whether the
estimated coefficient on F emale is statistically significant. [15%]

3.2. Does this regression suggest the presence of gender discrimination in earnings, that
is do female executives earn less than male executives? Explain. [15%]

3.3. Two new variables, the market value of the firm which is a measure of firm size (in
millions of dollars) and stock return (a measure of firm performance in % points)
are added to the regression:
\
ln(Earnings) = 3.86 − 0.28 F emale + 0.37 ln(M arketV alue) + 0.04 Return, (6)
(0.03) (0.04) (0.004) (0.03)

with N = 46, 670, and R̄2 = 0.345 (N is the sample size, and R̄2 denotes the
adjusted R2 ).
Why do you think the coefficient on F emale changed from the regression in equation
(5) to the regression in equation (6)? Explain. [15%]

4 Continued Overleaf
 3.4. Test for the statistical significance of Return. Can you conclude that firm perfor-
mance plays no economic role in explaining earnings? [15%]

4. Consider the following regression results from a random sample of 200 home sales:

P
\ rice = 109.7 + 0.567BDR + 0.239 Hsize + 0.1 Age − 56.9 P oor (7)
(22.1) (1.23) (0.021) (0.23) (12.23)

where P rice is the selling price of homes (in $1000), BDR is the number of bedrooms,
Hsize denotes the size of the house (in square feet), Age denotes the age of the house
(in years) and P oor is a binary variable that is equal to 1 if the condition of the house
is reported as “poor” and 0 if it is not. The numbers in parentheses are the standard
errors.
4.1. Test for the statistical significance of the coefficient on BDR. Is this result and the
regression in general consistent with the conventional wisdom that typically four
bedroom houses have a higher selling price than two bedroom houses? [15%]
4.2. A home-owner constructs a family room increasing the size of the house by 500
square feet. Construct a 95% confidence interval for the change in the value of their
house. [15%]
4.3. How would you modify the regression if you know that, ceteris paribus, the effect
of Age on price depends on whether the house is P oor or not? Explain. [15%]

4.4. Provide an economic reasoning to why this regression might suffer from heteroscedas-
ticity. How can you transform the equation so as to account for heteroscedasticity?
[15%]

Before your exam answers are collected:

Please ensure that you have written the course code (on the front of this
exam paper), your student ID, date of birth and the number of the question
that you have attempted on each answer sheet.

Put your exam answers in the order of the question number, ensuring that
yellow answer sheets follow the appropriate white answer sheet.

Do not place any other exam materials, including the exam paper, beside
the A3 answer sheets.

5 End of the Paper

 APPENDIX D: STATISTICAL TABLES 961

TABLE D.2 PERCENTAGE POINTS OF THE t DISTRIBUTION

Example
Pr (t > 2.086) = 0.025
Pr (t > 1.725) = 0.05 for df = 20 0.05
Pr (|t| > 1.725) = 0.10

t
0 1.725

Pr 0.25 0.10 0.05 0.025 0.01 0.005 0.001

df 0.50 0.20 0.10 0.05 0.02 0.010 0.002

1 1.000 3.078 6.314 12.706 31.821 63.657 318.31

2 0.816 1.886 2.920 4.303 6.965 9.925 22.327
3 0.765 1.638 2.353 3.182 4.541 5.841 10.214
4 0.741 1.533 2.132 2.776 3.747 4.604 7.173
5 0.727 1.476 2.015 2.571 3.365 4.032 5.893
6 0.718 1.440 1.943 2.447 3.143 3.707 5.208
7 0.711 1.415 1.895 2.365 2.998 3.499 4.785
8 0.706 1.397 1.860 2.306 2.896 3.355 4.501
9 0.703 1.383 1.833 2.262 2.821 3.250 4.297
10 0.700 1.372 1.812 2.228 2.764 3.169 4.144
11 0.697 1.363 1.796 2.201 2.718 3.106 4.025
12 0.695 1.356 1.782 2.179 2.681 3.055 3.930
13 0.694 1.350 1.771 2.160 2.650 3.012 3.852
14 0.692 1.345 1.761 2.145 2.624 2.977 3.787
15 0.691 1.341 1.753 2.131 2.602 2.947 3.733
16 0.690 1.337 1.746 2.120 2.583 2.921 3.686
17 0.689 1.333 1.740 2.110 2.567 2.898 3.646
18 0.688 1.330 1.734 2.101 2.552 2.878 3.610
19 0.688 1.328 1.729 2.093 2.539 2.861 3.579
20 0.687 1.325 1.725 2.086 2.528 2.845 3.552
21 0.686 1.323 1.721 2.080 2.518 2.831 3.527
22 0.686 1.321 1.717 2.074 2.508 2.819 3.505
23 0.685 1.319 1.714 2.069 2.500 2.807 3.485
24 0.685 1.318 1.711 2.064 2.492 2.797 3.467
25 0.684 1.316 1.708 2.060 2.485 2.787 3.450
26 0.684 1.315 1.706 2.056 2.479 2.779 3.435
27 0.684 1.314 1.703 2.052 2.473 2.771 3.421
28 0.683 1.313 1.701 2.048 2.467 2.763 3.408
29 0.683 1.311 1.699 2.045 2.462 2.756 3.396
30 0.683 1.310 1.697 2.042 2.457 2.750 3.385
40 0.681 1.303 1.684 2.021 2.423 2.704 3.307
60 0.679 1.296 1.671 2.000 2.390 2.660 3.232
120 0.677 1.289 1.658 1.980 2.358 2.617 3.160
∞ 0.674 1.282 1.645 1.960 2.326 2.576 3.090

Note: The smaller probability shown at the head of each column is the area in one tail; the larger probability
is the area in both tails.
Source: From E. S. Pearson and H. O. Hartley, eds., Biometrika Tables for Statisticians, vol. 1, 3d ed., table 12,
Cambridge University Press, New York, 1966. Reproduced by permission of the editors and trustees of Biometrika.