QBA25622 ASSIGNMENT PROJECT

Discipline of Finance, UTS.

Semester 1, 2015.
Subject Coordinator: Dr Otto Konstandatos
This assignment has several parts of unequal value. Some parts are technical, and are designed to help
you understand the connection between Mathematics and Econometric Regression Analysis.
You must type or neatly hand-write such answers in the spaces provided.
Other parts are applied, and are designed to help you develop practical econometric skills. You will
apply regression analysis as done by finance professionals using real world data. These parts will test
your econometric modelling skills using multiple regression and Eviews.
For these parts you may be required to report your Eviews output in the spaces below.
This assignment can be done in groups of up to five students. Your group members do not need to be
part of the same tutorial group. You must include this cover sheet. No names may be added to the
group lists apart from the names that appear below at hand-in. Submit only one assignment for each
group. DO NOT hand in a separate assignment for each group member. Late assignments will
require a Special Consideration application and will otherwise not be accepted.
Due Time/Date/Venue: The Student Centre will be collecting assignments this semester.
The assignment drop box is located in Building 5. There are no individual collection boxes for each
subject just ONE chute for all subjects. It is important to identify your assignment CLEARLY.
Submit your assignment by 12:00pm Thursday 28 May at Level 1 (street entry) Block C of
Building 5, located on the SIDE of the Student Centre (along the corridor) and NOT over the
counter. The assignment box is accessible 24 hours.

Name

Tutors Name:
Tutorial Day and Time:
Date stamp or tutors signature and date

Student Number

Group Work Protocol

Group work and group assignments are an important part of business education. The
purpose of group work goes beyond the requirements of the group project itself. Group
work is also intended to develop awareness of the dynamics of teamwork and your role in
a team environment. In undertaking group work it is expected that each team member
will communicate with other team members in a professional and courteous manner.
Resolving any conflict or difficulties that arise within the team is also part of the group
dynamics that may emerge during the project. It is expected that each team member will
take responsibility for managing and reducing any conflict that may arise. If the team
members are unable to resolve tensions or conflicts then this MUST be discussed with the
lecturer/tutor as soon as it becomes obvious that a resolution within the team cannot be
agreed.
In the learning environment of group work we are seeking to ensure that you develop and
demonstrate both academic skills and important group work skills such as:

Commitment to working with others (eg, undertaking a fair share of the work,
sharing ideas, doing the tasks allocated, attending meetings)

Collaboration and inclusiveness (eg encouraging and supporting others, respecting

others; recognising the skills and valuing the contribution of others, helping
resolve conflicts)

Contribution to establishing and working towards a common outcome (eg

establishing and supporting team goals, plans, rules, roles, decisions)

Group Work Declaration Form

Individuals must sign a declaration form, otherwise the project report will not be
marked. Complete only Part 1 or Part 2. Do not complete both. This sheet should be
completed and handed in along with your group assignment.
Part 1
I believe that all members of the group have contributed fairly to this assignment, and each member should
receive the same mark for the assignment.

Your name:.............................................................................Signature.........................................................

Group member names:

Part 2
I believe that not all members of the group have contributed fairly to this assignment. I believe the
proportion of the total workload that each has contributed is indicated below.
Your name..........................................................................Signature...........................................................

Group member names:

Proportion of Workload:

..%

..%

..%

..%

..%

Total = 100%
Please note that if you have signed Part 2 you must attach a statement explaining:

Why you believe a group member/group members have not contributed their fair share to
the project
A breakdown of tasks you and others have completed in the project
An estimate of the time you think each of those tasks has taken.
Any other positive or negative contributions made by you and others

This information will be shown to other group members so that they have an opportunity
to respond.
While each group members comments will be taken into consideration, the final
decision on how the marks are awarded will remain the right of the course coordinator.

Background.
The Cobb-Douglas production function is widely used by economists to represent the functional
relationship between a countrys real output (GDP) with the inputs Capital (K) and Labour (L). It is
named after American economists Charles Cobb (1875 1949) and Paul Douglas (1892 -1976), who
first tested this functional from against statistical evidence in the early twentieth century.
As we saw in lectures, the Cobb-Douglas function takes the form:

(1)

You are supplied with empirically gathered data, summarising the normalised GDP output for
Australia from the years 1965 to 2008 with the corresponding indexes for Labor and Capital inputs for
each year. Your task is to undertake a study to estimate the Cobb-Douglas production function from
the given set of data in the spreadsheet ausdata.xlsx. The variables are as follows:
Y = Index of total production, namely the value of all goods produced in the given year.
K = Index of total value of all Capital input in the given year.
L = Index of total value of all Labour input in the given year.
The constant C is the total factor productivity. It represents all the factors influencing total production
not accounted for by the inputs Capital and Labour.
The constant is called the Output Elasticity for Capital. The constant is the Output Elasticity for
Labour. The output elasticities determine the ceteris-paribus responsiveness of Total Production
(output Y) to a change in levels of Capital and Labour respectively. When the output elasticities
satisfy the extra restriction:

+ = 1 (2)
the model will display constant returns to scale, so that a doubling of the inputs of Labor and Capital
will lead to a doubling of production.
Your task is to use econometric modelling to estimate the constants C, and for Australias CobbDouglas production function (1), using the linearised model:

ln = 0 + 1 ln + 2 ln +
Please enter all your answers into the provided spaces below.

(3)

Part 1: Deriving the Least Squares Estimators

Recall, in Linear Least Squares, we have to estimate the line of best fit which
minimizes the sum of squared deviations of the data. This is equivalent to choosing
parameters (b0 , b1 ) which minimises the function of two variables (namely SSR):
n

SSR f (b0 , b1 ) ( y i b0 b1 xi ) 2 .
i 1

You will use calculus to show that f (b0 , b1 ) is minimized for the choices:
n

b1 1

where x

(x
i 1

x )( y i y )

(x
i 1
n

b0 0 y b1 x

x)2

1
1
xi and y y i .

n i 1
n i 1

You may assume the following summation properties in your solution (see Lecture 5):
n

If k is a constant,

k nk .
i 1

Given u i and v i for i 1 n , then

i 1

i 1

i 1

(aui bvi ) a ui b vi .

Differentiating a summation (the derivative of the sums equals the sum of the
derivatives):
n
n
f i ( x, y )
f i ( x, y )
n
n
f
(
x
,
y
)

and
f
(
x
,
y
)

i
i
x i 1
x
y i 1
y
i 1
i 1

Q1 (1 mark): In lectures we saw that the total deviation about the mean is always zero,
n

i.e.

(x
i 1

x ) 0 . Expand the summation across the brackets and apply this result to the
n

yi to prove that:
Ans:

(x
i 1

x )( y i y )

x (y
i 1

y) .

Q2 (1 mark) Prove that

=1

(xi x)2 =

x
=1 i

(xi x)

Ans:

Q3 (2 marks): By differentiating the summation, show that

f (b0 , b1 ) 0 when
b0

b0 0 y b1 x .
Ans:

Q4 (1 mark): Differentiate the summation with respect to b1 to get a summation

expression for
f (b0 , b1 ) .
b1
Ans:

Q5 (2 marks): Prove that by choosing b0 and b1 to minimize

(y
i 1

b0 b1 xi ) 2 you

obtain the least squares estimators, namely:

n

b1 1

(x
i 1

(x
i 1

Ans:

x )( y i y )
i

x)2

b0 0 y b1 x

Q6. (1 mark): Given the data in the supplied spreadsheet, can you estimate the Cobb-Douglas
production function in the form of Equation (1) ( = ) directly using Eviews and Linear
Least Squares? If not, why not?
Ans:

Q7. (1 mark): A production function has constant returns to scale if doubling the inputs of
Capital (K) and Labour (L) doubles the total output (Y). If the output elasticities satisfy restriction
(2), prove that the Cobb-Douglas production function (1) exhibits constant returns to scale.
Is this still true if the restriction given by Equation (2) is relaxed?
Ans:

Q8. (1 mark): Take the natural logarithm of both sides of the equation to obtain a linear model of
the form:

ln(Y ) B0 B1 ln( K ) B2 ln( L)

for some coefficients 0 , 1 and 2 . What is the relationship between these coefficients and the
parameters of the original non-linear model given by Equation (1)?
Ans:

Q9. (1 mark): Read the data into Eviews and transform the supplied data to estimate the coefficients
0 , 1 and 2 in the linearised regression given by Equation (3). Cut and paste your Eviews output
below. (Note: Eviews uses the function log(x) for Natural logarithm, i.e. log base e).
Ans:

Q10. (1 mark) Comment on the sign of the estimated coefficients 1 and 2 , and state whether this is
what you expect. Ignore significance at this stage.
Ans:

Q11 (1 mark) Formulate and carry out an appropriate hypothesis test, to test whether Capital (K)
affects Australias output, Y. Use the t-statistic approach, at the =0.05 level.
Ans:

Q12 (1 mark) Formulate and carry out a hypothesis test for testing whether Labour (L) affects
Australias economic output, Y. Use the p-values approach, at the =0.05 level.
Include any Eviews output in your answer.
Ans:

Q13 (1 mark) Test the following joint hypothesis about the coefficients B1 and B2:
H0: B1 0 and B2 0 , H1: B1 0 or B2 0 , with =0.05.
Along with the previous results, what do you conclude about Capital and Labours significance for
explaining Australias GDP output?
Ans:

Q14 (2 marks) Test the following hypotheses for the coefficients B1 and B2. Clearly specify the
rejection region if you are using critical values, and clearly state your conclusions.
When using p-values, calculate and compare your p-values to the test size then state your conclusion.
Assume the Central Limit Theorem holds.
(a) H0: B1 0 ,
(b) H0: B1 0 ,
(c) H0: B2 0 ,
(d) H0: B2 0 ,

H1: B1 0 , with =0.05 using the critical-value approach.

H1: B1 0 , with =0.05 using the critical-value approach.
H1: B2 0 , with =0.05 using the p-value approach.
H1: B2 0 , with =0.05 using the p-value approach.

Ans:

Q15 (1 mark) An economist thinks that the Australian economy displays increasing returns to scale,
and consults you for help using your econometric expertise. Formulate a hypothesis test on the
regression coefficients in Q8 to test for increasing returns to scale using the data.
Do not perform the hypothesis test.
Ans:

Q16 (2 marks) Using re-parametrisation, convert the regression in Q8 to perform the hypothesis test
you formulated in Q15. Set up and run the re-parametrised regression model in Eviews. Copy and
paste the results of your re-parametrised Eviews regression and state your conclusion, at the 1% level.
Ans: