ETW3420 Principals of Forecasting and Applications Group Assignment 1
Principals of Forecasting and Applications
Copyright By PowCoder代写 加微信 powcoder
Group Assignment 1
Semester 2, 2022
DUE DATE: Friday, 16 September 2022, 4.30pm
The unit learning objectives of this assignment are:
• Motivate the need for obtaining reliable forecasts in business and economics
• Understand and apply appropriate statistical methods for business and economic fore-
• Develop computer skills for forecasting from business and economic time series data
• Provide practical insights from your forecasts
INSTRUCTIONS
1. This is an DUO group assignment worth 25% of your final mark for this unit. The
total number of marks for this assignment is 100.
2. Make sure that you regularly make back-up copies of your work. Computer, disk, or
cloud problems will not be accepted as valid reasons for late submissions or requests
for extensions.
3. Students should pay particular emphasis on the narration, and how the results are
presented and interpreted. Students should endeavor to ensure that the report is
complete and well-composed. Poor presentation, poor command of English
writing and/or failure to comply with instructions may result in a mark
4. Your report should be no more than 15 pages (excluding Graphs, Reference
List, and Appendix). Any part of the report beyond the 15 page limit will be struck
out and not marked.
(a) Use default format, paragraph, and margin settings.
(b) Font size: 12
(c) At least 1.2 line spacing between lines.
(d) Graphs should be appropriately sized and easy to read. They should not be made
small to conserve space.
(e) Penalties may apply if the assignment does not conform to the formatting guide-
5. With regards to graphs and estimation outputs:
(a) All graphs should be in-line with the text for ease of reading, and not placed
in an Appendix at the end of the report.
(b) Any raw R output can be labelled and placed in an Appendix at the end of
the report. Otherwise, if reporting any estimation output within the report, the
output should be professionally presented in a table format.
6. Students must uphold academic integrity at all times. Any students caught for contract
cheating, plagiarizing or permitting others to plagiarize their work will be reported to
the Responsible Officer for academic misconduct in accordance to the Student Aca-
demic Misconduct Procedure. Severe penalties may apply resulting from the investi-
7. All submissions will be via Moodle.
(a) If you choose to type your assignment in Microsoft Word, you will need to save
it as a PDF file and submit (i) the PDF document, (ii) the Excel dataset (.csv
format), and (iii) the R-script file consisting of the codes used to perform your
(b) If you choose to type your assignment using Rmarkdown, you will need to submit
(i) the PDF form of the assignment, (ii) the Excel dataset (.csv format), and (iii)
the RMD file.
(c) You will also be required to put your assignment through a Turnitin report.
The similarity index should not be more than 15%. Note that this is only a rough
guideline – we understand that some common usage of phrases and sentences
may contribute to the similarity index. Students should not be worried for this
particular instance.
8. All submissions should be submitted with an Assignment Cover Sheet attached.
ASSIGNMENT TASK
Assignment Aim
To quantify the forecasted loss in US revenue passenger miles since the COVID-19 pandemic.
Instructions
Proceed with the prescribed Forecasting Process below. Write a research report based on
your analysis. Your report should include tables and graphs and an associated narrative.
Keep the report concise and clear. Thoughtfulness, clarity of your discussion and the com-
munication of your results are important.
The Appendix does not constitute part of the 15-page limit.
Stage 1: Define Goal [10 marks]
• Provide a brief background of revenue passenger miles as an airline traffic statistic in
the United States by referring to appropriate academic/news article citations.
• Subsequently, provide a narration of how the COVID-19 pandemic has impacted the
airline industry in the United States.
• In relation to the Assignment Aim above, define the goal of the forecasting problem
that you are going to address in this report.
– You will gain a better understanding of the purpose of this forecasting exercise
after completing this assignment. Hence, it is advised to write this part of the
introduction after completing the other assignment tasks below.
• Students should write no more than 1 page for this Stage.
Stage 2: Get Data [2 marks]
• You will obtain data on US revenue passenger miles from the CEIC database.
This database contains numerous datasets on economic and business data of countries
around the world.
The Teaching Team will provide your student email to CEIC who will manually register
each student. An automated email will then be sent to students respectively to setup
your password.
Below are the CEIC details after receiving the automated email:
CEIC CDM Next Platform URL: https://insights.ceicdata.com
Username: (registered email address)
Password: Click on “Forgot Password” to reset
Each user has up to 3 browser/device accesses and each new browser access will require
a PIN which will be automatically sent to the registered email address.
Any issues or queries can be sent to either Ms. or
the Helpdesk team :
• When you have logged into the CEIC database, search for the monthly Air Carrier
Traffic: Revenue Passenger Miles for United States from the ‘Global Database’
• Download the revenue passenger miles dataset ranging from January 1996 to April
• Import the data into RStudio to begin your analysis, doing the needful to convert it
into a time-series object.
• For this Stage in the assignment, no detailed write-up is required. However, for the
purpose of completeness of presentation, you can just briefly write a sentence stating
where the data was obtained from. This part of the assignment is mainly to give
students first-hand experience of searching for and downloading data from a database.
Stage 3: Explore and Visualize Time Series [10 marks]
• Plot suitable time series graphics. Do not plot graphs for the sake of plotting them –
be selective on the number and type of graphs you want to display.
• Describe in detail your time series graphics, making sure to identify any patterns or
outliers. If applicable, are there any particular explanations as to why your data plots
display certain interesting features (e.g. what event happened to explain a sudden jump
or drop in data)?
https://insights.ceicdata.com
Stage 4: Pre-Process Data [3 marks]
• Based on your data visualization, determine the choice of your time span. That is,
determine how far back into the past you want to consider for this assignment.
• In other words, for the rest of the assignment, decide if you want to use the full data
set from January 1996 to April 2022, or if you want to exclude a portion of the data
whereby the resulting start date of your reduced data set is later than January 1996.
Be sure to justify your answer.
• Note that the last time point of your data set should still be April 2022. It is the
starting date of your data set that you should decide on.
• The resulting data set from this stage will be referred to as the “full dataset”.
Stage 5: Partition Series [5 marks]
• First, using your full dataset defined from Stage 4, partition your series into two parts
labelled as “Pre-Covid” and “Covid”.
– The “Pre-Covid” part comprises of data prior to the start of the pandemic in the
United States.
– Ensure that the “Covid” part comprises of data that coincides with the time frame
when the United States was affected by the pandemic.
• Next, divide the “Pre-Covid” dataset into a training set and test set. Be sure to
state the time periods over which your training and test sets span, respectively. Also
report the number of observations in each of these sets.
Stage 6: Apply Forecasting Methods/Models [30 marks]
• Using appropriate tools and methods, identify
(i) ONE of the four simple forecasting methods from Topic 3 and
(ii) TWO ETS exponential smoothing models
that you would consider using for forecasting. Justify your answers.
• Using the training set data, fit your identified forecasting method/models from above,
and also use the ets() function in R to automatically select an ETS model. Report
the ETS model selected by R.
You should have a total of FOUR forecasting method/models.
Note: In some cases, it is possible that your identified ETS model selected might
coincide with the ETS model chosen by the ets() function. In this case, then you will
have THREE forecasting method/models.
• For the exponential smoothing models, report the parameter estimates and initial
values, along with some summary measures of the within-sample forecast residuals
in a table. What can you infer from the magnitude of some of the estimated smoothing
parameters?
• Produce separate plots of the training set data with the fitted values from each of the
method/models. Ensure that your plots are correctly labelled. Comment on the plots.
• Perform residual diagnostic checks for all the method/models.
• Which of the above method/models has the best goodness of fit? Explain if this is
what you expected.
• Use each of the above method/models to produce forecasts for the test set period.
Subsequently, plot the “Pre-Covid” data set (i.e. both training and test set data),
along with the forecasts produced by the 4 forecasting methods/models.
– Do not include prediction intervals in the plot.
– Make sure that your axes are labeled correctly, along with the chart title.
– Make sure that you insert a legend in the plot, correctly labeling the various
forecasts.
• Describe the forecast plots in detail, giving explanations as to why the test set forecasts
produced by the above methods/models look as such.
Stage 7: Evaluate and Compare Forecasting Performance [20
• Evaluate the out-of-sample forecast accuracy of the 4 forecasting method/models by
using the traditional approach. Be sure to articulate the process on how you did this
evaluation. Which method/models forecasts best?
• Evaluate the forecasting performance of the 4 method/models using time series cross-
validation with a forecast horizon of h = 12. Do you come to the same conclusion?
• Which forecasting method/model would you finally select for producing forecasts?
Stage 8: Implement Forecasts [10 marks]
• Using your selected forecasting method/model from Stage 7, re-estimate the parameters
using the “Pre-Covid” data set.
• Report the new estimated parameter values in a table, if applicable.
• Using the new set of estimated parameters, produce forecasts for the “Covid” time
• Produce a plot of the full dataset (see Stage 4) with the forecasts. Ensure the plot is
labeled correctly.
• Describe the pattern of the forecasts, including the forecast intervals. Do they look
reasonable?
• Compare the forecasts with the actual revenue passenger miles in the “Covid” time
Stage 9: Quantifying the Forecasted Loss in Revenue Passenger
Miles [10 marks]
• Using all the results obtained so far,
– Calculate the forecasted loss in revenue passenger miles (in billions) sustained by
the United States since the start of the pandemic.
– Calculate a range of forecasted loss in revenue passenger miles.
• To conclude the report, provide a summary of what has been done and some policy
recommendations based on your results.
INSTRUCTIONS
ASSIGNMENT TASK
Assignment Aim
Instructions
Stage 1: Define Goal [10 marks]
Stage 2: Get Data [2 marks]
Stage 3: Explore and Visualize Time Series [10 marks]
Stage 4: Pre-Process Data [3 marks]
Stage 5: Partition Series [5 marks]
Stage 6: Apply Forecasting Methods/Models [30 marks]
Stage 7: Evaluate and Compare Forecasting Performance [20 marks]
Stage 8: Implement Forecasts [10 marks]
Stage 9: Quantifying the Forecasted Loss in Revenue Passenger Miles [10 marks]
程序代写 CS代考 加微信: powcoder QQ: 1823890830 Email: powcoder@163.com