ECON1061 – Forecasting and Quantitative Analysis
Assessment 3: Final Assessment
Instructions:
This is an open-book assessment. It is to be completed individually. The assessment is not a hurdle requirement - that is, you don't have to pass the assessment in order to pass this course. You need an aggregate of 50% or more in all assessments in order to pass the course.
Scope: There is no page or word limit.
Submission: Via Assignments folder in Canvas.
Marks: The assessment is worth 40 marks and accounts for 40% of the total grade for this course.
Academic integrity: This is an individual piece of assessment. Submission will be verified via Turnitin for any form. of plagiarism. The assessment should contain your own work and you can’t copy or have someone else complete any part of the work for you. By submitting this assessment, you are declaring that you have read, understood and you agree to the content and expectations of the Assessment declaration: https://www.rmit.edu.au/students/my-course/assessment-results/assessment
Presentation Instructions:
Your submission should comply with the following presentation standards:
1. Typed using a standard professional font type. Font “Arial” size 11 is recommended.
2. Pages should be numbered.
3. Label your answer to each question clearly – e.g., Question 1 a.
4. There is no page or word limit.
5. Graphs and tables should be clearly labelled and presented.
6. Your work should be well-presented with no spelling, typographical and grammatical errors.
7. Answer all questions in a new Word document. DO NOT copy the questions as this will affect your Turnitin score.
8. Delivered as a Word (.doc or .docx) or PDF (.pdf) file.
Question 1
The below output shows the results of an ARIMA model which was fitted to a time-series data of Australia’s GDP, and an excerpt of the data. Based on the below model and information:
|
Quarter, Year
|
GDP (in trillions of dollars)
|
|
Q1, 2023
|
6.5
|
|
Q2, 2023
|
7.5
|
|
Q3, 2023
|
8.0
|
## Series: GDP
## Model: ARIMA(1,1,0)
## Coefficients:
## ar1 constant
## 2.5 0.6
a) Explain what the time series is likely to look like (i.e., cyclical, seasonal, with a trend).
b) Calculate the predicted GDP value for Q4, 2023? (6 marks)
Question 2
The following ACF plots were produced for raw data of monthly sales of two different variables, A and B.
Explain which variable (A or B) is likely to be easier to forecast.
Explain how your answer to part a) would change if these were residuals of an ARIMA model instead of “raw data of monthly sales”.
Explain which variable (if any) is likely more seasonal?
Variable A:
Variable B:
(6 marks)
Question 3
The following monthly production of beer (in megalitres) have been recorded for January, February, March, and April, respectively: 200, 202, 205, 208. Examining the forecasting accuracy for the month of April only, explain which of the following forecasting method would you recommend: the Naïve method, the Average method, or the Simple exponential smoothing method (assuming alpha=0.75 and initial state of 190)? (3 marks)
Make sure you load the fpp2 and fpp3 library before you answer Questions 4-6.
Question 4
This question requires you to use the dataset, global_economy. Your task is to analyse the Exports for France and use at least two forecasting techniques you have learnt in the course to forecast Exports for the next 10 years. Pay attention to whether the data needs to be transformed. Discuss all your results carefully, writing down estimated models where required and performing model evaluation. The analysis needs to be thorough. (10 marks)
Question 5
This question requires you to use the dataset, aus_production. Your task is to 1) conduct a thorough analysis of Beer production; 2) use an appropriate ARIMA (from the class of ARIMA models you have learnt in the course) to forecast Beer production for the next 4 years. Pay attention to whether the data needs to be transformed. Discuss your results carefully. Write down the estimated model(s) where required and perform. model evaluation. The analysis needs to be thorough. (10 marks)
Question 6
This question requires you to use the dataset, us_change that contains information on percentage changes in quarterly personal consumption expenditure, savings and a few other variables. Your task is to forecast Consumption based on Savings. You will use the dynamic regression approach (regression with additional ARIMA errors) to predict Consumption for the next 10 quarters. After estimating the regression model, when making predictions, assume that the future percentage changes in savings is 2%. Evaluate the model. (5 marks)