This case study is designed for students to apply the concepts and techniques learned in lectures to a real-world problem. Students will analyse the characteristics of the All Ordinaries Index, and forecast its PE ratio at the end of June 2017. Several variables related to the All Ordinaries Index are contained in the file “CaseData.xlsx” which can be downloaded from the subject website under “Case Study”. Variable definitions are provided in the data file. Students are encouraged to seek additional data to facilitate their analyses. This case study accounts for 20% of the final mark for the subject.
[6 marks] Define the hold-out period as Mar 2015 to Feb 2017. Use MSE to
compare forecasting performance. Select up to 5 explanatory variables (but not
necessarily 5) and estimate the corresponding regression model to forecast PE at the end of June 2017. Briefly explain why these variables are selected. There are a few reports posted on the subject website under “Case Study” that will help select variables and determine the model. You need to ensure that the regression model satisfies the underlying assumptions. You can use the full sample or a sub-sample to estimate your model. Please justify your sample selection and report the in- sample estimated coefficients in Table 2 below. Fill in the sample period and replace X’s with variable names.
Table 2: Regression Results
|[sample period]||Coefficient||t stat||p value|
AdjR2 Model F stat DW
Compare the forecasting performance of DMA, SES, and Holt’s in the hold-out period, using the optimal parameters when required. Compare the forecasting performance of the best of DMA, SES, and Holt’s against the linear regression. Report the following table based on the hold-out period.
Table 3: Optimal Parameters and MSE
|In-sample opt parameters||MSE in hold-out period|
Use the best model from above analyses to forecast PE at the end of June 2017. Check if your forecast is within the 95% confidence interval constructed from your sample.
Case Study Team
We encourage students to form teams of up to 5 members to complete the case study. There is no interference from the lecturers on the formation of the team and changes of team members. Teams with more than 5 members attract a penalty. For each person over the limit, 20% of the full mark is deducted. For example, case reports with 6 members will be marked out of 16 instead of 20.
Submission of the Case Report
Parts 1 to 3 of the case study are due on Wednesday May 3 at 9 pm. Parts 4 and 5 are due on Wednesday June 1 at 9 pm. A submission box will be available on Level 4 of Building 8. Case reports deposited after the due date attract a penalty. For each business day, or part of a business day the case study is late, 20% of the full mark is deducted. For example, case reports received 2 days after the May 3 will be marked out of 6 instead of 10. An EXCEL file with the details of your analyses should be electronically submitted using the UTSOnline ‘Digital Drop Box’.
Quality of Writing (2 marks)
- The report should have a clear structure that addresses the above issues.
- Paragraphs should be clearly connected and coherent. Each paragraph should start with a topic sentence. The sentences flow logically from point to point.
- Written expressions should be clear, complete, and grammatically correct.
- All tables and graphs should be referenced and discussed in the text of the
Unreferenced tables and graphs will not be considered.
- Sources of information should be fully referenced in the text with details provided in the reference list.
- To help prepare your report you may find it useful to read the Guide to Writing Assignments available at: http://www.uts.edu.au/sites/default/files/business-
- The report should have a cover page containing subject number and name, report title, team members: name, ID, and UTS email.
- The all-inclusive page limit is 15, including the cover, text, tables, graphs, and the
reference list. To comply with the page limit, you need to carefully structure the report and the paragraphs and carefully design the tables and graphs. Any materials beyond the page limit will not be considered.
- All text should be double space with 12 size font.
- Structure your spreadsheet so that the lecturer can understand it easily. Do not email your spreadsheet as it will not be opened or examined. We may inspect your spreadsheet if we have any concerns with your repo