ECMT2130 Financial Econometrics Semester 1, 2024
GROUP PROJECT
DUE: 11.59pm Friday, 24th of May 2024
Academic Honesty
Academic honesty is a core value of the University, and all students are required to act
honestly, ethically and with integrity. The consequences of engaging in plagiarism and
academic dishonesty, along with the process by which they are determined and applied, are
set out in the Academic Honesty in Coursework Policy 2015. Under the same policy, as the
lecturer, I must report any suspected plagiarism or academic dishonesty.
General Instructions
• This is a group assignment which accounts for 20% of your final mark.
• Please type your answers (no handwriting). Make sure to compile all your answers in a
single PDF file and submit it via Canvas. You can only submit your work once, so please
double check everything before submitting.
• There are 16 questions in this assignment. Please attempt all questions.
• I will randomly select 5 questions to mark, and each question is worth 4 points. The total
number of points of this assignment is therefore 20. The grading will be based on the
completion and general quality of your submission.
• Refer to the group spreadsheet (link here) to find out which ASX200 company your group
has been allocated to. Failure to work with the correct series will result in loss of 10
marks and you might be referred to the Academic Integrity team.
• Answer all questions in a neat PDF document (no other extensions accepted). Use Times
New Roman font size 12 throughout the report and normal margins. Make sure any
images/screenshots included in the document are pasted in high definition: your report
should look neat, clean, professional and easy to navigate. Failure to follow this
instruction will result in a loss of 5 marks.
• Only the group leader is required to submit the final report and other files. Please, make
sure to include a cover sheet with the SIDs of the group members, their signatures and the
series assigned to the group. I made one available on the submission box.
• Based on University policy, a late submission is subject to a penalty of 5% (of the total
points) per calendar day; and work submitted more than 10 days after the due date will
receive a mark of zero.
• You are required to work with R and Excel (no other software allowed). In addition to
your report, you are required to submit your R script and Excel spreadsheet. Include brief
explanations of what you have done in both these files (if we don’t understand what was
done, we will consider it incorrect).
• You are welcome to seek clarification/help from the teaching team, particularly with R
and Excel. But the help will be naturally limited.
2
PREPARATION
Each group is assigned a company listed in the Australian Stock Exchange (ASX). Once
groups are formed completely, a ticker (a unique identification symbol representing the
company in the stock exchange) will be placed on column G (named “ticker”). The earlier
this process is completed the earlier you can start working on your project.
Once you have been assigned a ticker, open the R script (Data.R) and fill line 8 with your
ticker. Follow line 9 as an example. Run the code and the result should be an Excel
spreadsheet containing information on the stock price of your company and the
corresponding returns. Take some time to familiarise yourself with the R script provided.
You’re now ready to answer the questions.
QUESTIONS
Throughout the assignment, I will symbolise the series of (close) share price as and the
corresponding series of returns with . The time span you should use is the one specified in
the “Data.R” script provided, i.e., from the 1st of January 2021 until the 24th of April 2024.
Using your assigned financial time series, answer the following questions:
1) Provide a brief overview of what the company you have been selected does. Make sure to
include the goods/services it commercialises, number of clients, where it operates in the
world, its main competitors and its last general financial figures. Your answer should be at
most half a page.
2) If the Efficient Market Hypothesis (EMH) is true, do you expect to find a good model to
forecast the conditional mean of ? Briefly explain.
3) Plot . Make sure to include labels on the y and x axes, as well as a title. Describe its
main features from a classical decomposition perspective. Hint: you might want to have a
look at the lecture slides on this again.
4) Calculate the average, standard deviation, minimum, maximum, skewness and kurtosis of
your series of prices and return series over the time span specified. Place them all on a neat
table, preferably prepared in Excel (do not copy and paste the R output). Interpret the kurtosis
of your series.
3
5) Propose a histogram for and another one for . Using the graphs and the basic statistics
obtained in question 4, indicate whether the sampling distributions of price and return are
visually normally distributed. Feel free to overlay a normal distribution on top of the
histograms to strengthen your argument and/or use statistical tests of normality.
6) Calculate the Sharpe ratio for and for the market proxy (ASX200 returns). You will
need to find the return of the risk-free asset for the relevant period. Briefly justify why you
selected such a risk-free rate.
7) Calculate the alpha and beta of your assigned share. Interpret both values. Do you have
evidence pro or against the CAPM in your case? Make sure to indicate the null hypothesis of
your tests in the explanation. Hint: be careful here with the number of observations for both
dependent and independent variables.
8) Using the data from 01/01/2021 until 31/12/2023, fit the following models to :
(i) Drift.
(ii) Mean.
(iii) Naïve.
(iv) Seasonal Naïve.
Using the test set (data from 01/01/2024 until the last observed point), evaluate which model
fits the data best. Use the RMSE as the criterion. Plot a graph of the series of prices and fitted
values of your best model in the same picture. Forecast the next seven business days of data
using your favourite model.
9) Fit the following models to :
(i) Simple Exponential Smoothing (SES).
(ii) Holt’s linear trend.
(iii) Holt-Winters.
Using the entire dataset here, which model fits the data better using the MAPE? Justify your
choice. Forecast the next seven business days of data using your favourite model. Make sure
to include 95% confidence intervals around the forecasts.
10) Is a stationary series? Use the plot of the returns, the ACF and the KPSS test to justify
your claim. Apply an appropriate level of differencing, if necessary. If you do, show that the
transformed series is now stationary using the KPSS test.
11) Using the ACF and PACF of the (potentially differenced) return series, propose a suitable
ARMA model. Explain how you obtained your answer and write out the model specification.
Compare this model with a simple model regressed on a constant only (with specification
= + ). Use an information criterion of your choice to decide.
4
12) Using your preferred ARIMA(p, d, q) model, produce forecasts for the next seven
business days. Make sure to calculate the 95% forecasting intervals.
13) Using actual data from Yahoo Finance or equivalent, pick the model (from Q8, Q9 and
Q12) that best forecasted the next five business days of . Contrast this with what you
expected in Q2.
14) Using , propose an ARCH(1), ARCH(2) and ARCH(3) model. Are the parameter
conditions met? Which one seems most appropriate for your data? Justify your answer. Plot
the fitted variance of the returns.
15) Using , propose a GARCH(1,1) model. Plot the fitted variance of the returns. Are the
period(s) of high observed volatility in the graphs in Q3 consistent with the predicted
volatility generated by the GARCH(1,1) model? Forecast the conditional variance for the
next seven business days.
16) Assuming the return series follows a normal distribution, use the estimated mean and
standard deviation you calculated in Q4 to estimate the 1%-VaR of your series. Produce
forecasts for the 1%-VaR for the next seven business days using your best model for the
conditional mean and the conditional standard deviation.