– This is an individual assignment. It should reflect your individual effort
– The assignment should be typed, with the main tables, charts and results presented
throughout the assignment to highlight your responses to the questions
– There should be no appendices (appendices will not be marked)
– Marks will be awarded for neatness, conciseness and clarity of answers
– Where answers call for explanation, a simple reporting of numerically correct results
will yield few (if any) marks
– When conducting hypothesis tests, outline all steps in your answer
– Maximum number of pages allowed: 10 (additional
pages will not be marked)
– Pages should be numbered
– Be as concise as you can, while clearly addressing each question
– Total marks: 30
Submission instructions
– You are required to submit the assignment in both print and electronic copies
– Electronic submission is via a submission link on
iLearn
– Print copy (with a signed assignment coversheet) must be submitted at BESS (E4B) –
ensure you know your tutor’s name, as there will be separate submission boxes for
each tutor
– A link to the FBE cover sheet is provided under the “Assignment” heading on iLearn
Fill in
the details of the cover sheet and staple it to the front of your assignment
Part 1
Part 1 – Total number of marks: 15
The Eviews workfile “Part1_Assignment_Workfile.wf1” located under “Assignment” heading
on iLearn contains four series for the period June 1972 – February 2016 (525 observations).
The following variables are included:
- Monthly prices for
cvs
(CVS Health which is a U.S. pharmaceutical company)
- Returns on three pricing factors from Fama and French (1993)
_mkt rf
Market Risk Premium
hml
High minus Low
smb
Small minus Big
rf
(the U.S. risk free rate)
Answer the following questions based on this dataset:
- How are the factors computed and what do they represent? (Hint: Look at the Fama
and French 1993 paper – its on iLearn). Briefly describe major company characteristics
of CVS Health. (2 marks)
- Create
log returns (in percent, e.g. 3.25%) and name them _.r cvs Calculate the excess
return on
cvs
stock as
_r cvs rf–
and name it _.er cvs Consider the following
model:
er cvs mkt rf hml smbb bbbe=+ + + +
What signs (positive or negative) would you expect to estimate for each of the factors?
__
Why? (3 marks)
01 2 3
ttttt
- Estimate the model in B and present the fitted equation. Interpret the fitted
coefficients. Which parameters are statistically significant at the 5% level? Are the
estimated parameters of the same
sign as you expected in B? (4 marks)
- Conduct a test for the validity of the CAPM. What do you find? (3 marks)
- Conduct the basic diagnostic tests on the estimated model, i.e. autocorrelation (use 4
lags of residuals), heteroskedasticity (no cross product), non-normality,
misspecification of functional
form (only quadratic term). Comment on your results
and suggest remedies to any problems you may detect. (You are NOT required to
carry out the remedy to any problem you may detect. If you see a problem, state what
it is and simply describe what could be done). (3 marks)
Part 2
Part 2 – Total number of marks: 15
The Eviews workfile “Part2_Assignment_Workfile.wf1” located under “Assignment” heading
on iLearn contains daily adjusted closing price for Qantas from 01 Jan 2007 to 12 April 2016,
which is 2,414 daily observations. It is designated “Qan” in the workfile.
- Plot a graph of the Qantas
share price, and comment on its salient features. Conduct
an ADF unit-root test on the price series. Be careful to properly state the null and
alternative hypothesis for the test. Comment on your findings.
(2 marks)
- Generate a new variable for the daily log returns (in percentage terms)
for Qantas.
Name this variable
_.r qan
Present a graph of the return series along with summary
statistics, and comment. Conduct a KPSS unit-root test on the returns for Qantas. Be
careful to properly state the null and alternative hypothesis for the test. Comment on
your findings.
(2 marks)
- Plot the ACF and PACF functions
for Qantas returns (include 5 lags). On the basis of
these results, you decide to estimate three models for Qantas returns. They are:
rqan b e=+ (1)
_
_
1
tt
r qan b be e
=+ + (2)
–
121
ttt
r qan r qanb be
=+ + (3)
Which model do you think is the best from among these three?
(2 marks)
__
–
12 1
ttt
- Re-estimate the model you selected in Part C by adding, respectively, an i) ARCH(5),
- ii) GARCH(1,1) and iii) GJR(1,1,1) specification. What are these models, and how do
they differ? Report the fitted
equations, comment on the output, including a careful
interpretation of the parameters in the volatility equation, and compare across the
three specifications. Provide graphs of the estimated conditional variances and
comment on them. Overall, which one of the three specifications do you prefer?
(9 marks)
References
Fama, E. F. and
French, K. R. (1993). “Common risk factors in the returns on stocks
and bonds”. Journal of Financial Economics 33(3), 3-56.