PURPOSE

The Individual Assignment relates to the following Learning Outcomes:

•   Apply econometric methods to modelling, analysing and forecasting financial data

•    Demonstrate and explain different estimation methodologies.

•   Critically evaluate empirical econometric work.

These learning outcomes support development of the following Graduate Capabilities:

•    Discipline Specific Knowledge and Skills

•    Critical, Analytical and Integrative Thinking

• Effective Communication

SUBMISSION

•   The assignment must be submitted via Turnitin by 11.55pm on Wednesday 10 May 2023. The submission link is available on iLearn under the “Assignment” tab from 5pm on Monday 1 May.

•   No  extensions  will  be  granted,  except  in  cases  where  an  application for “Special Consideration” has been made and approved.

•    Late submission will incur a penalty of 5% per day of total available marks.

•   Submissions will not be accepted beyond 96 hours past submission deadline unless an application for Special Consideration has been made and approved.

•   You can only submit ONCE to Turnitin.  See the “After-submission checklist” (on page

2) for what you need to check after submitting.

•   Note: there is no “expected” range for similarity reports. You may get a high or low   number. The issue is this: Have you produced your own work? The similarity report   allows the lecturer to quickly check your submission against others for originality. A  high similarity report will be a problem if you have not quoted your sources, or included more quotes than your own work, or your work is substantially the same as another’s. Check thislinkfor more information: https://www.plagiarism.org/article/quoting-material

•   Marks will be assigned based on the quality of the responses to each question and in line with the rubric at the end of this document.

PLAGIARISM

•   Avoid plagiarism. The consequence of plagiarism is a zero mark.

•   You may work with other students at the preparatory stage. However, the final version of the assignment should be written in your own words.

•   Note that Turnitin will compare your submission against others’ as well as internet sources and any submission you have made in previous sessions in any unit.

•    Get familiarised with the academic honesty policy :

https://staff.mq.edu.au/work/strategy-planning-and-governance/university-policies- and-procedures/policies/academic-honesty

DOCUMENT PREPARATION CHECKLIST

Submit   your   assignment   with   the   file   name:   FamilyName_GiveName_Student

ID_ Econ3034Assignment.

For example: Smith_ Mary_ 12345678_ Econ3034Assignment

All  questions  involving  calculations  must  show all steps  involved to  arrive  at your

answer.

You have used Equation Editor. In MS Word go to: “Insert” then “Equation” . All questions requiring a written response must include all relevant reasoning.

All written answers are typed and then saved as a  pdf. You  cannot submit  a  hand

written document.

You can NOT submit a pages (Mac) document.

You  can  NOT  submit  photos  of  your  assignment.  It  must  be  written  using  word

processing software and then saved and submitted as a pdf.

All answers are presented in the same sequence as the questions in the assignment. All answers are written in full sentences and in clear language.

All answers are proofread and grammatical errors and typos are minimised. Your submission should be in size 12 font.

The master document is saved as a pdf file of less than 40MB.

If you try to submit, and get a message that reads “Error M14:11” or similar, then you

have tried to upload a Word document.  Save as a pdf and re-submit.

Include page numbers.

Do not include appendices.

Do not go beyond 15 pages.

AFTER-SUBMISSION CHECKLIST

I have double-checked whether the document was properly uploaded.

I have seen my originality report.

I have received the Turnitin receipt via email.

Part 1

Part 1 - Total number of marks: 32

The ‘Assignment_Question 1 EViews Workfile’ located under the ‘Assignment’ heading on iLearn contains seven monthly return series for the period January 1980 – February 2020 (482 observations).

The following monthly return series appear in the file:

A.  The excess return on a portfolio of stocks of U.S. companies in two different industries. The first industry is manufacturing, and the second industry is retail. The data on the portfolio industry excess returns are from the website of Kenneth French under Industry Portfolios.

• manuf _ rf (Average monthly excess return on a portfolio of manufacturing industry stocks. The manufacturing stocks are listed on U.S. exchanges and the return is in excess of the U.S. risk free rate).

• retail _ rf (Average monthly excess return on a portfolio of retail industry  stocks. The stocks in the retail industry are listed on U.S. exchanges and the return is in excess of the U.S. risk free rate).

B.   Returns on five pricing factors from Fama and French, also on the website of Kenneth French.

• mkt _ rf (Excess return on a weighted portfolio of all stocks in the U.S. market. It is the U.S. Market Risk Premium).

• hml (High minus Low. Average monthly return on a portfolio of High Book-to- Market (Value) stocks less the average monthly return on a portfolio of Low Book-to-Market (Growth) stocks).

• smb (Small minus Big. Average monthly return on a portfolio of small capitalization stocks less the average monthly return on a portfolio of large (big) capitalization stocks).

• rmw (Robust minus Weak. Average monthly return on a portfolio of stocks for companies with robust operating profitability less the average monthly return on a portfolio of stocks for companies with weak operating profitability).

• cma (Conservative minus Aggressive. Average monthly return on a portfolio of stocks of companies which invest conservatively less the average monthly return on a portfolio of stocks of companies which invest aggressively).

To read about the factors, mkt _ rf , hml and smb, search under Fama-French three factor model and to read about the factors rmw and cma search under Fama-French five factor    model.

Note: All of the returns are expressed in percent, e.g., 2.65% is represented by 2.65, not by 0.0265. Also, please see the document ‘How to save images from AppStream’ on our iLearn

site under ‘Assignment’ in order to obtain an image of a table or graph in EViews. Answer the following questions based on this dataset:

1.          Estimate the following regression for the excess return on the portfolio of manufacturing stocks for the full sample 1980m01 to 2020m02 and include a table of results from EViews.

manuf _ rft = β1 + β2 mkt _ rft + β3hmlt + β4 smbt + β5rmwt + β6 cmat + ut Are the estimated coefficients on the five factors jointly statistically significant at the 5% level? (2 marks)

2.          For the manufacturing stocks regression, perform a test of the hypothesis that

β3 − β4  = 0 against the alternative that β3 − β4  ≠ 0, using EViews. What do you conclude? (2 marks)

3.          Estimate the following regression for the excess return on the portfolio of retail      stocks for the full sample 1980M01 to 2020M02 and include a table of results from EViews.

retail _ rft = β1 + β2 mkt _ rft + β3hmlt + β4 smbt + β5rmwt + β6 cmat + ut Are the estimated coefficients on the five factors jointly statistically significant at the 5% level? (2 marks)

4.          For the retail industry stocks regression, perform a test of the hypothesis that

β3 − β5  = 0 against the alternative that β3 − β5  ≠ 0, using EViews. What do you conclude? (2 marks)

5.          Interpret the estimated value of the coefficient β2   in the two regressions. Is the estimated coefficient statistically different from one in each case? (Perform the test in EViews). What do you conclude about the sensitivity of each portfolio to the market risk premium? (4 marks)

6.          Compare the corresponding estimated coefficients on the other factors in terms of

their sign and significance in both regressions (i.e., compare the estimated coefficient on hml in the manufacturing stocks regression with that in the retail stocks regression. Do similarly for the estimated coefficients on smb, rmw and cma. What does this comparison suggest about the average characteristics of stocks in the manufacturing and retail industries? (Hint: For example, are manufacturing stocks value stocks on average, etc?). (8 marks)

7.          Is the estimate of β1  statistically significant at the 5% level in each of the regressions? How do you interpret this result?   (4 marks)

8.          Perform White’s test (with no cross-product terms) for heteroscedasticity in the estimated residuals from each regression. (Write out the null and alternative hypotheses of the test, explain and provide the EViews output showing the results, and clearly state the conclusion of the test. Use a 5% significance level). (2 marks)

9.          Perform the Breusch-Godfrey test for serial correlation up to order four. (Write out the null and alternative hypotheses of the test, explain and provide the EViews output showing the results, and clearly state the conclusion of the test. Use a 5% significance level). (2 marks)

10.        In view of the results you found in parts 8 and 9, should you be concerned about heteroscedasticity and/or serial correlation. If so, what should you do, and would that change any of the conclusions you reached in earlier questions. (4 marks)

Part 2

Part 2 - Total number of marks: 28

The ‘Assignment_Question 2 EViews Workfile’ located under the ‘Assignment’ heading on   iLearn contains three monthly yield series for the period January 2005 – February 2023, i.e., from 2005M01 to 2023M02. The series bbb _ 10yr is the yield to maturity on BBB grade corporate bonds and the series gb _ 10yr is the yield to maturity on 10-yr government bonds. The series spread is the bbb _ 10yr yield less the gb _ 10yr yield. The data is obtained from the Reserve Bank of Australia. The yields are represented, for example, as 6.95 which means 6.95% per year.

11.        Using EViews, graph the spread series. Describe the main features seen in the graph and provide an economic explanation for these features. (4 marks)

12.       Conduct an ADF unit-root test on the spread series. Be sure to state the null and alternative hypothesis for the test. Also conduct a KPSS unit root test and be sure to state the null and alternative hypothesis for the test. Are the results from both tests consistent with each other? (4 marks)

13.       Compute the ACF and PACF for the spread for the first 12 lags using EViews. Comment on the pattern of the ACF and PACF. On that basis, what do you think is the most appropriate time series model to estimate. Justify your answer. (4 marks)

14.       Consider the following two models where yt denotes the series for spread : Model 1: yt = c1 + φ1yt−1 + 91ut−1 + ut

Model 2: yt = c2  + φ1yt−1 + φ2yt−2  + ut

Estimate each model in EViews. Comment of the significance of the coefficients (apart from the constant) and indicate whether each model is stationary. Select the  best model using the Akaike Information Criteria (AIC) and the Schwarz Bayesian Information criteria (SBIC). (Hint: Sample sizes need to be the same when comparing models with AIC or SBIC. That is, estimate the models over the sample period 2005M03 to 2023M02 (i.e., beginning in March 2005) because model 2, which has    the most AR lags, namely two, uses up two observations for the lags in the estimation. In the equation estimation settings box, change 2005M01 to 2005M03). (6 marks)

15.        Using EViews, compute the ACF and PACF of the residuals (out to 12 lags) for Model

2. Comment on the results. (2 marks)

16.        Estimate Model 2 for the sample 2005M03 to 2020M12 and generate a dynamic forecast for the period 2021M01 to 2023M02. (Hint: First estimate Model 2 being    sure to specify 2005M03 2020M12 in the estimation settings box. Having estimated the model, select the forecast tab, select dynamic forecast, set the forecast sample to 2021M01 to 2023M02, and in the forecast name box, type spread _ df .

(i)         EViews generates a graph for the dynamic forecasts you generated together with the two-standard error band. Present this graph and comment on the    convergence or otherwise of the forecast values and on the behaviour of the two-standard error band. (4 marks)

(ii)        Graph the actual spread series and the dynamic forecast of the spread

series i.e., spread _ df on the same graph for the period 2021M01 to 2023M02. (Hint: Click on Quick/Sample and specify the sample as 2021M01 2023M02. Click OK. Then, on the main menu bar at the top of the screen,    click on Object/New Object/Group and OK. In the list of series box, type spread and spread _ df and click OK. Then click on View/Graph to graph    both series together). Comment on the graph. (4 marks)