Forecasting

Need a good Stat Expert to solve two questions

I need a good stat expert to solve 2 questions.I will let you know which 2 questions later but the question pattern will be exactly similar

However, this needs to be solved in a 2.15 hour

Sample question attached.I will provide you the live question at 10 am Singapore time

ANL317 Copyright © 2020 Singapore University of Social Sciences (SUSS) Page 1 of 8
Timed Online Assignment – January Semester 2020
ANL317 Timed Online Assignment – January Semester 2020
Forecasting Tuesday, 12 May 2020 10:00 am – 12:30 pm
____________________________________________________________________________________
Time allowed: 2.5 hours
____________________________________________________________________________________
INSTRUCTIONS TO STUDENTS:
1. This Timed Online Assignment contains FIVE (5) questions and comprises EIGHT (8) pages (including cover page).
2. You must answer ALL questions.
3. If you have any queries about a question, or believe there is an error in the question, while the assignment is in session, briefly explain your understanding of and assumptions about that question before attempting it.
4. Upon completion of your assignment, submit it online via Canvas (similar to Tutor Marked Assignment (TMA) submission).
5. Your submission is to consist of only one file and of no more than 500MB in size. The file must be a Microsoft Word file saved in .docx format. All answers are to be typed. Flowcharts and graphs may be scanned or photographed and embedded in the Word file provided it does not exceed the file size limit of 500MB. Images of text will not be marked.
6. Please submit your answers at the end time of your assignment. Thereafter, you will not be able to submit your answers and you will be considered as having withdrawn from the course. No appeal will be allowed.
7. To prevent plagiarism and collusion, your submission will be reviewed by Turnitin. The Turnitin report will only be made available to the markers and you will not be able to view it after the submission deadline.
ANL317 Copyright © 2020 Singapore University of Social Sciences (SUSS) Page 2 of 8
Timed Online Assignment – January Semester 2020
8. The University takes plagiarism and collusion seriously, and your Turnitin report will be examined thoroughly as part of the marking process.
ANL317 Copyright © 2020 Singapore University of Social Sciences (SUSS) Page 3 of 8
Timed Online Assignment – January Semester 2020
Answer all questions. (Total 100 marks)
Question 1
The yield on a city bond fluctuates with the market. The monthly quotations for January-June 2017 are given in Table 1-1.
Table 1-1: Monthly yield on the city bond for 2017
Month
Yield
January
9.29
February
9.99
March
10.16
April
10.25
May
10.61
June
11.07
(a) Forecast the monthly yield for the bond, starting from April, using a three-month moving average.
(7 marks)
(b) Forecast the monthly yield for the bond, starting from June, using a five-month moving average.
(5 marks)
(c) Evaluate the two (2) forecasting methods using the MAPE (minimum absolute percentage error).
(8 marks)
ANL317 Copyright © 2020 Singapore University of Social Sciences (SUSS) Page 4 of 8
Timed Online Assignment – January Semester 2020
Question 2
Mr. Ng is a trader in the commodity market. He has followed the corn price for a few years and would like to use an ARIMA model for forecasting. The time series plot of the price (in cents) per bushel of corn for 120 consecutive months is shown in Figure 2-1. The autocorrelation plot of the corn price is shown in Figure 2-2. After some transformation, the sample autocorrelation function and sample partial autocorrelation function of the transformed data are shown in Figure 2-3 and Figure 2-4.
Figure 2-1: Time series plot of the corn price
Figure 2-2: Autocorrelation function for the corn price
ANL317 Copyright © 2020 Singapore University of Social Sciences (SUSS) Page 5 of 8
Timed Online Assignment – January Semester 2020
Figure 2-3: Autocorrelation function for the transformed data
Figure 2-4: Partial autocorrelation function for the transformed data
(a) Describe the transformation that Mr. Ng has likely performed on the original price series. Justify your answer.
(10 marks)
(b) Based on the information given, determine an appropriate ARIMA model the corn price is likely to follow. Your answer should include relevant details and justification.
(10 marks)
ANL317 Copyright © 2020 Singapore University of Social Sciences (SUSS) Page 6 of 8
Timed Online Assignment – January Semester 2020
Question 3
Asuss Airline would like to forecast the number of passengers who will fly from Singapore to Shanghai in 2018. The data is given in Table 3-1. The consultant first developed a time series regression model, using time as the independent variable and the number of passengers as the dependent variable to fit the data. The fitted line is shown in Figure 3-1, and the autocorrelation function for the residuals obtained from the regression model is shown in Figure 3-2.
Table 3-1: Number of passengers flying from Singapore to Shanghai
Year
Number of passengers (1,000s)
Year
Number of passengers (1,000s)
1993
22.8
2006
69.9
1994
26.1
2007
79.9
1995
29.4
2008
96.3
1996
34.5
2009
109.0
1997
37.6
2010
116.0
1998
40.3
2011
117.2
1999
39.5
2012
124.9
2000
45.4
2013
136.6
2001
46.3
2014
144.8
2002
45.8
2015
147.9
2003
48.0
2016
150.1
2004
54.6
2017
151.9
2005
61.9
Figure 3-1: Fitted line plot
ANL317 Copyright © 2020 Singapore University of Social Sciences (SUSS) Page 7 of 8
Timed Online Assignment – January Semester 2020
Figure 3-2: Autocorrelation function for residuals
(a) Write down the regression model with the unknown coefficients.
(3 marks)
(b) Examine whether the assumption of independent errors for this model is violated. Justify your answer.
(4 marks)
(c) After applying another two models, the fitted models are specified as follow:
??????(????????????? ??????)=3.123+0.083?? ????????????? ??????=22.716∗1.086??
Based on these two models, forecast the number of passengers for 2018. (Note: log is short for logarithm.)
(10 marks)
(d) In general, how should the consultant decide which model to use for forecasting?
(3 marks)
ANL317 Copyright © 2020 Singapore University of Social Sciences (SUSS) Page 8 of 8
Timed Online Assignment – January Semester 2020
Question 4
Jim works as an analyst in a fast food delivery company. He was given data of weekly orders for Burger King and Swensen’s in the East, Central and West of Singapore, and was asked to forecast the orders for the coming week. He decided to use a hierarchical method. After some analyses, the aggregate order forecast for the coming week is 200, and the order forecasts for Burger King and Swensen’s are 60 and 160 respectively. The Burger King order forecast for the East, Central and West regions are 20, 30 and 10, respectively, and the Swensen’s order forecast for the three regions (i.e., East, Central and West) are 40, 60 and 80, respectively.
(a) Draw a diagram (without reconciliation) with the forecasted values displaying the hierarchy levels as described above.
(5 marks)
(b) Describe the top-down, middle-out, and bottom-up reconciliation methods. Construct one (1) model for each of these methods based on the forecast values used in your diagram from part (a).
(9 marks)
(c) Discuss one (1) advantage of forecasting using hierarchies. Which reconciliation method is preferred? Justify your answer.
(6 marks)
Question 5
Consider the dynamic regression model:
????=1.5+0.5????−1+1.4????+0.7????−1+????
At time ??∗, there is a step intervention of one-unit increase in ??, which means that ?? remains one unit higher permanently since time ??∗.
(a) Identify the estimated effect on ?? at ??∗,??∗+1, and ??∗+2.
(7 marks)
(b) Identify the permanent effect on ??.
(5 marks)
(c) If the intervention is a pulse intervention (which means that ?? increases by one-unit at time ??∗, and immediately returns to its former level at time ??∗+1), what will be the permanent effect on ??? Compare it to your answer for 5(b).
(8 marks)
—– END OF PAPER —–