ASSIGNMENTS This group assignment is worth 50% of your overall grade and is broken down into three parts

ASSIGNMENTS

This group assignment is worth 50% of your overall grade and is broken down into three parts.
Each part will be marked out of 30. The first part is worth 10% while the second and third parts
are worth 20% each. Students are to form groups consisting of no less than 3 students and
no more than 5 students. Full marks will be awarded if the assignments are completed to a
satisfactory standard. Each group is to submit a soft copy through Turnitin, by 11:59pm
on the day of submission. All submissions of assignments must be accompanied by an
assignment cover sheet that details the names and student ID numbers of the members of the
group. Work on computer disks will not be accessed. Permission to submit assignments by
email will not be granted under any circumstances.
Marks will be deducted if:
? Submissions from one group have clearly been plagiarised from another group, with only
minor changes in wording or formatting,
? Assignments are incomplete,
? The assignment was submitted after the due date without adequate reason, or
? The work is of a very poor standard; that is, the standard econometric techniques taught in
the course have not been used.
In these assignments, you will look at two case studies. The first case study looks at the
determinants of the Australian dollar exchange rate using the monetary approach to exchange
rate determination. In the second, the effect of the Global Financial Crisis on the shares of
Apple Inc. is analysed. When working through these case studies, you should not ignore
information you have found in previous tutorials.
For the questions that follow, you may use either Excel or EViews. It is recommended that you
become familiar with both programs as you will find that each program does some things more
easily than the other. However, as you progress through your assignment, you should try to
become more proficient in the use of EViews.

Note: When you are asked to calculate the returns, or take the natural logarithms of the
variables, do NOT print them all out and include them in your submission. The graphs
and calculations you produce are sufficient.

CASE STUDY ONE
In this Case Study, you will look at modelling the Australian dollar vis-á-vis the New Zealand
dollar exchange rate, using a conventional monetary model. The data you will use is in the file
called “The Monetary Model.xls”. This contains the following data: ‘S(AUD/NZD)’ ??ts
, which

is the Australian dollar per NZ dollar exchange rate; ‘Aust. MS’ ??tm

, which is the level of the
Australian money supply; ‘NZ MS’ ??*tm , which is the level of the New Zealand money supply;
‘Aust. GDP’ ??ty

, which is a measure of Australian gross domestic product (GDP); ‘NZ GDP’
??*ty , which is a measure of New Zealand gross domestic product (GDP); ‘Aust. IR’ ??ti , which
is a measure of short-term Australian interest rates, and ‘NZ IR’ ??*ti , which is a measure of
short-term New Zealand interest rates. Data on these variables were collected from the IMF’s
International Financial Statistics database, and from the Reserve Bank of Australia’s website.
To begin the empirical analysis, make sure you take the natural logarithm of S(AUD/NZD), Aust.
MS, NZ MS, Aust. GDP, and NZ GDP. Leave the interest rate variables, Aust. IR and NZ IR, in
their raw form. Also, use a level of significance of ? = 0.05 for all tests in this study.
(a) Calculate the correlation between the spot exchange rate and all the other variables. Which
variable has the strongest correlation with the exchange rate? I will call this variable
“PREDICTOR” in the questions that follow. (4 marks)
(b) Calculate the mean, median and mode of the spot exchange rate. What is the difference
between these types of “averages”? Compare the values of the mean and median. State
what you think is the most appropriate average for this set of data, giving brief reasons for
your answer. (4 marks)
(c) Draw a histogram of the spot exchange rate. Calculate the variance, measure of skewness
and kurtosis. Using the descriptive statistics that you have calculated, do they indicate that
the data is symmetric, and is this confirmed by the value of the skewness? Comment on the
value of kurtosis. Based on these results, say why you believe that the spot exchange rate
does, or does not, have a normal distribution. (6 marks)
(d) Write some brief notes, in point form, describing your results for Case Study One. Be sure
to report any conclusions that you have made, and submit these. You will use them in a
later tutorial when you write your final report. (2 marks)
CASE STUDY TWO

Assignment

3Bachelor of Business
RMIT & SIM, Economics, Finance & Marketing
ECON1272 Basic Econometrics
In this Case Study, you will be looking at the effect of the Global Financial Crisis (GFC) and the
Great Recession on Apple stock. In the file called “Apple Inc.xls”, there is monthly data from
June, 2001 to June, 2016, on the share price of Apple stock and the Dow Jones Industrials.
You will be looking at a number of important dates: December 2007, when the GFC and the
Great Recession had officially begun, September, 2008, when the US Government allowed
Lehman Brothers, an Investment Bank, to go bankrupt, and June, 2009, when the National
Bureau of Economic Research (NBER) declared that the Great Recession had ended.
(a) Obtain line graphs for both the share price of Apple stock and the Dow Jones Industrial
average, over the whole period and comment on any similarities or differences between
them. (2 marks)
(b) Calculate the continuous returns on both indices. Obtain histograms and descriptive
statistics up to, and including the November 2007, and then from December 2007 onwards.
Comment on any similarities or differences between them. (2 marks)
(c) For the Apple stock, calculate the 95% confidence intervals for the mean return over the two
periods given in part (b). Use the critical t-values from the following website:
https://www.easycalculation.com/statistics/t-distribution-critical-value-table.php (4 marks)
(d) Assume that the returns on the Apple stock has a normal distribution. Using the means and
standard deviations previously calculated for each of the two periods, find the probability of
getting a negative return on a day selected at random. (4 marks)
(e) Write some brief notes, in point form, describing your results for Case Study Two. Be sure
to report any conclusions that you have made, and submit these. You will use them in a
later tutorial when you write your final report. (2 marks)

CASE STUDY ONE - continued
In this section, you will estimate a simple linear regression model to fit the exchange rate. From
Assignment One, choose the input variable that has the strongest correlation with the exchange
rate that you believe will produce a good model (this is the variable that we called
“PREDICTOR”).
Following on from Assignment One, use the same data set and a level of significance of ? =
0.05 for all tests in this study.
(a) Draw the scatter diagram for these two variables. (2 marks)
(b) Estimate the model to predict the exchange rate. How much of the variation in the
exchange rate is explained by your model? Is this statistically significant? Test to see
whether the intercept is required in your model. (4 marks)
(c) Obtain a graph of the residuals vis-á-vis the independent variable for part (b). Is there any
evidence of problems? (4 marks)

CASE STUDY TWO - continued
In the next stage of this study, you will estimate betas for the Apple stock vis-á-vis the US
market using the data in the file called, “Apple Inc.xls”. You will need the returns you
calculated from a previous tutorial. You will also use the two sub-periods you used before, that
is, up to and including November 2007, and then from December 2007 onwards. In this
analysis, you will treat Apple as the share and the Dow Jones Industrial average as the market.
(a) Draw scatter plots of the two pairs of returns you will use for estimating the market models.
(4 marks)
(b) For the two sets of returns in each of the two sub-periods, find the betas using the Market
model:

tMttituRR???
10??

Here the dependent variable is the ‘raw’ or ‘actual returns’ ( itR

) for the Apple stock and the

independent variable is the ‘actual market returns’ ( MttR

) on the Dow Jones Industrial
average. Once you have estimated these betas use the ‘F’ statistic and the value of R 2 to
evaluate these estimated models. (4 marks)
(c) For both sub-periods, test to see whether the Apple stock is neutral or aggressive using ? =
0.05. That is, test whether 11??

. (5 marks)
(d) For the first sub-period, estimate the Scholes-Williams Beta and Dimson’s Beta. Do you
think you need to use this sort of adjustment here? (5 marks)
(e) Write some brief notes, in point form, describing your results for Case Study Two. Be sure
to report any conclusions that you have made, and submit these. You will use them in a later
tutorial when you write your final report. (2 marks)

CASE STUDY ONE - continued
Consider the model you fitted in Assignment Two, Case Study One, part (b).
(a) Test to see if the errors are autocorrelated. If autocorrelation is present, suggest possible
reasons why. Try to correct it by including the appropriate number of autoregressive
moving average (ARMA) terms. Use the critical Durbin-Watson values at the 5 per cent
level of significance from the following website:

http://web.stanford.edu/~clint/bench/dw05b.htm (3 marks)
(b) Test to see if the errors are heteroscedastic. If it is present, obtain an improved set of
estimates for the t-statistics. (2 marks)
(c) Test to see if the errors are normally distributed. Based on the results of the three tests you
have carried out, how reliable do you think the estimation and test statistics are? (2 marks)
(d) Now estimate a new Multiple Regression Model that uses all of the variables, as well as
your original PREDICTOR variable, but excludes the ARMA terms. That is
t
*
tt
*

tttttuiiyyPREDICTORms????????
6543210???????

(2 marks)
(e) Identify the coefficients with large p-values. Eliminate the variable with the largest p-value,
and re-estimate the new equation. Repeat this procedure until the only variables left in the
model have coefficients for which the p-value is less than ? = 0.05. Show the output for this
final model (This is called the ‘top-down’ approach). (3 marks)
(f) Use the F-test for redundant variables to determine whether the joint impact of all the
variables that you have excluded is significant. (2 marks)
(g) Based on the results of part (f), and any other tests you think are necessary, choose a
model you think contains all the relevant variables. (1 marks)
(h) Obtain a set of (static) forecasts (that excludes the ARMA terms) for the Australian dollar
exchange rate. Asses the quality of your forecasts using the various error measures
generated internally by EViews, when you made your forecasts. Write a brief report
discussing your results. You should comment on the reliability of your estimation and test
procedures, the variables that are most important in explaining the exchange rate, and how
well your model predicts the exchange rate. (3 marks)

CASE STUDY TWO - continued

Returning to the Case Study Two, you will investigate if there have been any significant
changes in the market models. To do this, you should first generate some dummy variables.
The first additive dummy variable, DA1, should equal zero up until November, 2007, one
between December 2007 and June 2009, and zero from July 2009 onwards. This period
corresponds to when the GFC and the Great Recessions is considered to have officially begun,
and when the NBER declared that the GFC and the Great Recession had ended.
The second additive dummy variable, DA2, should equal zero up until November, 2007, and
then one from December 2007 onwards. This period corresponds to the onset and continuance
of the GFC and the Great Recession, according to commentators like Robert J. Gordon and
John B. Taylor.
The first event dummy variable, DE1, should have a value of zero, except for September 2008,
when it will have the value of one, and zero elsewhere. This corresponds to the month when
the US Government allowed Lehman Brothers, an Investment Bank, to go bankrupt.
The second event dummy variable, DE2 should have a value of zero, except for June 2009,
when it will have the value of one, and zero elsewhere. This corresponds to when the US
Government officially declared that the GFC and the Great Recession had ‘ended’.

(a) Estimate a market model for the entirety of the sample period. Include only the additive
dummy variable DA1, and the event dummy, DE1. What do you conclude? (3 marks)
(b) Now estimate a second market model for the entirety of the sample period, but this time
include only DA2 and DE2. What do you conclude? (3 marks)
(c) Test to see if the models estimated in parts (a) and (b) contain any first-order
autocorrelation. If they do, correct for it by including the appropriate number of ARMA terms.
(2 marks)
(d) Using the appropriate t and F-tests, see if there are any differences in the models, as a
result of the GFC and the Great Recession. (2 marks)

(e) Using your answers to the above questions, and the notes from the previous tutorials, briefly
discuss whether the GFC and the Great Recession had any effect on the performance of
Apple’s share price (Do this in a couple of paragraphs). (2 marks)