Economics 309
Applied Financial and Economic Forecasting
Professor:
Stanley Holmes, Ph.D.
Email:
[email protected]
Office:
BA 132D
Phone:
(903) 468-6029 or (903) 365-7190
Fax:
(903) 886-5601
Semester Project
The objective of the project is to simulate a problem you might face in your first job or business—developing the best 2 year forecast for company sales. Forecasting is an important process in almost all businesses and is an important skill to possess as an employee. The project is due by midnight Central Time on 12/2/2013. You are strongly encouraged to spread the work throughout the semester.
1. Selecting independent (X) variables for your project
Hopefully you have all passed this stage. You need to pick X variable quarterly data sets. Make sure the data are NOT seasonally adjusted. The data relationships should be logical and not spurious. For example, do not use the price of hamburger to forecast auto sales.
2. Writing an abstract
After you pick your topic, it is a good idea to write a brief abstract to help focus your thoughts. The abstract should not be more than a page. It should include
(i) State your forecasting problem- develop the best forecast of each variable.
(ii) Information about and description of your data
(iii) Description of your proposed models
3. Body of the paper
The paper will contain detailed explanations of your thought processes and methodology. At every stage you need to answer the following questions for each variable:
(i) What did you do (ex: Winter’s method with these parameter values…)
(ii) Why did you do it?
(iii) What did you find? (Interpretation of your results)
(iv) What is your conclusion?
Remember this is a business project report for your company – Do Not Show failed model attempts. Show only the best model for each variable for each forecast method.
4. Methodology
The body of your paper will include all four major forecasting techniques:
(i)
Smoothing for each X variable (Chapters 8): You need explain what, why, how etc.
(ii)
Box-Jenkins for each X variable (Chapters 9, 10, 11, 12):
(iii) Decomposition for each X variable (Chapter 7)
(iv) Multiple Regression forecast of the sales variable (Y) (Chapter 3, 4, 5 and 6): You will need other variable(s) to help explain the variation in the sales variable of interest. You need to start looking for those explanatory (X) variables!!
5. Appendix
Your appendix should contain all the relevant supporting printouts such as the tests, plots, graphs etc. that were not used in the discussion in the body of the presentation. It is better to divide the appendix into parts where each part is representing the output from each methodology (ex: Appendix A: Variable Data and citations, Appendix B: X variable outputs, Appendix C: Sales Revenue outputs). Don’t forget to name or number the appendices, you will need to refer to them when you are talking about a specific methodology.
6. Final Report
Your final report shoul ...
Economics 309Applied Financial and Economic ForecastingProfe.docx
1. Economics 309
Applied Financial and Economic Forecasting
Professor:
Stanley Holmes, Ph.D.
Email:
[email protected]
Office:
BA 132D
Phone:
(903) 468-6029 or (903) 365-7190
Fax:
(903) 886-5601
Semester Project
The objective of the project is to simulate a problem you might
face in your first job or business—developing the best 2 year
forecast for company sales. Forecasting is an important process
in almost all businesses and is an important skill to possess as
an employee. The project is due by midnight Central Time on
12/2/2013. You are strongly encouraged to spread the work
2. throughout the semester.
1. Selecting independent (X) variables for your project
Hopefully you have all passed this stage. You need to pick X
variable quarterly data sets. Make sure the data are NOT
seasonally adjusted. The data relationships should be logical
and not spurious. For example, do not use the price of
hamburger to forecast auto sales.
2. Writing an abstract
After you pick your topic, it is a good idea to write a brief
abstract to help focus your thoughts. The abstract should not be
more than a page. It should include
(i) State your forecasting problem- develop the best forecast of
each variable.
(ii) Information about and description of your data
(iii) Description of your proposed models
3. Body of the paper
The paper will contain detailed explanations of your thought
processes and methodology. At every stage you need to answer
the following questions for each variable:
(i) What did you do (ex: Winter’s method with these parameter
values…)
(ii) Why did you do it?
(iii) What did you find? (Interpretation of your results)
(iv) What is your conclusion?
Remember this is a business project report for your company –
Do Not Show failed model attempts. Show only the best model
for each variable for each forecast method.
4. Methodology
3. The body of your paper will include all four major forecasting
techniques:
(i)
Smoothing for each X variable (Chapters 8): You need explain
what, why, how etc.
(ii)
Box-Jenkins for each X variable (Chapters 9, 10, 11, 12):
(iii) Decomposition for each X variable (Chapter 7)
(iv) Multiple Regression forecast of the sales variable (Y)
(Chapter 3, 4, 5 and 6): You will need other variable(s) to help
explain the variation in the sales variable of interest. You need
to start looking for those explanatory (X) variables!!
5. Appendix
Your appendix should contain all the relevant supporting
printouts such as the tests, plots, graphs etc. that were not used
in the discussion in the body of the presentation. It is better to
divide the appendix into parts where each part is representing
the output from each methodology (ex: Appendix A: Variable
Data and citations, Appendix B: X variable outputs, Appendix
C: Sales Revenue outputs). Don’t forget to name or number the
appendices, you will need to refer to them when you are talking
about a specific methodology.
6. Final Report
Your final report should include anexecutive summary of your
findings which will include the conclusions (Which of the
techniques works best and why for each X variable?). You can
add the results to your abstract and make the abstract into an
executive summary. You need to have an introductionto talk
about your topic in greater length. It will include above
sections 3, 4 and 5 and a conclusion. Be detailed and complete
in all your sections. This is a case of more is better than less as
you explain to me what you have done.
4. � Please remember that there is NOT one right way of
preparing a paper. Be precise, explain everything in detail and
be structured. The outline is ONLY to remind you about the
required parts; its arrangement is completely up to you.
RevenueJ.C. PennyGAPSearsBest BuyCostcoWalMartTarget
DirectTVDISHDisneyNetflixGeicoAetnaAflacUnitedHealth
GroupAppleMicrosoftDELL Auto ZoneOReilly Auto PartsWD-
40AT&TVerizonFord MotorGM ChryslerToyotaHersheyHibbett
SportsDicks Sporitng GoodsSports AuthorityHome
DepotLowesAMD IntelJet BlueU.S. AirwaysAmerican
AirlinesSouthwest Airlines United AirlinesUPS
FedExDateRevenueDateSalesDateRevenueDateRevenueDateRev
enueDateRevenueDateRevenueDateRevenueDateRevenueDate
RevenueDateSalesDateRevenueDateRevenue
DateRevenueDateRevenueDateRevenueDateRevenueDateSalesD
ateSalesDateRevenueDateSalesDateRevenueDateRevenueDateSa
lesDateRevenueDateRevenueDateRevenueDateRevenueDateSale
sDateRevenueDateRevenueDateSalesDateSalesDateRevenueDat
eRevenueDateSalesDateRevenueDateRevenueDateRevenueDate
Revenue
DateSalesDateRevenue3/31/9543673/31/95848.6883/31/957443
3/31/951947.1113/31/954307.32183/31/895373.25983/31/89282
63/31/953566.83/31/9540.4133/31/80218.13/29/0230.5273/31/9
5951.312/29/006598.43/31/951713.6763/31/951103.8353/31/95
26523/31/9515873/31/951135.9333/31/95364.0613/31/9542.766
3/30/9022.5433/31/9551643/31/953449.73/31/95347839/30/092
67843/31/1097006/29/0133477403/31/95867.4469/30/9620.6181
2/31/043642070003/31/98155.2173/31/953568.9623/31/951634.
693/31/95627.3813/31/9535573/29/02133.3693/31/0516283/31/
9839603/31/95611.7133/31/951408.3433/29/9653359/29/891647
.4536/30/9544356/30/95868.5146/30/9584406/30/951274.6966/
30/953896.2386/30/896046.41316/30/8930976/30/953708.56/30
23. data. You can refer to the project outline for further details.
You may also download and save the data as an EXCEL file.
The first column should be the dates and second column should
be your data. Always label your columns appropriately.
3. Go to one of the approved data sources. This time you will
need to obtain minimum 3 related variables. These variables
should be values determined outside of the firm. (Not company
accounting data) We will call these related variables the X
variables. These variables will be quarterly consistent with your
Y variable (If your Y variable is quarterly, your X variables
will also be quarterly). All variables should be from the same
time period. You can refer to the project outline for further
details.
4. As an option for one of the three X variables you may Ggo to
the company web site, annual reports or 10-K SEC filings and
obtain any relevant internal data that you wish to include as
another X variable. This could be R&D Expenses, Marketing
Expenses, Total Expenses Product Units, Employees, etc. that
you believe are important to the output of the company. Make
sure that this variable is quarterly as well and covers the same
time as the Y variable.
5. As another option for one of the three X variables you may
go to the company data in Doc Sharing and see if you can find
either competitor companies or companies that produce goods
that are complimentary to your assigned company. You may
also look for competitors sales data from 10-Ks and annual
reports. Remember that this must also cover the entire time
period you have for the assigned Y data. You may use the
revenue/sales figures for these companies as another X variable.
6. Download and save all your X variables in your Minitab
project worksheet labeled appropriately and save Minitab
project. You may also save them as an EXCEL file. Recall that
the first column is dates and second column is your Y variable.
Your third column will be X1, 4th will be X2 and so forth.
24. Label your X variables properly so I can understand what those
variables are.
7. At this point you should have a copy of dates (C1), Y
variable (C2) and X variables (C3 – C5) in a MINITAB project
worksheet. Make sure that the variable columns are labeled
correctly so I can understand which variables you are analyzing.
8. Run individual “Time Series Plots” and “ACF” on all your
variables. Note the Trend, Cycle and Seasonality
characteristics that are indicated by these plots. Note which X
variable trend, cycle and seasonality characteristics are similar
to the Y variable characteristics.
9. Produce descriptive statistics for all your variables.
Comment on the mean, range and standard deviation and what
they indicate relative to each variable.
10. Run Scatter plots of Y against each X separately. Note the
linearity of the relationship. Classify it as positive or negative,
weak, moderate or strong.
11. Develop and show the correlation matrix (you can find it
under Stat>Basic Statistics>Correlation) of Y and all Xs. Enter
the Y values first followed by each X that you have in order of
the data columns. You need to tell me which Xs are more
related to Y and which Xs are not. You need to prove that the
relationships are statistically significant.
12. Your proposal should be a word document and include the
pasted relevant Minitab output as well as the, the data used in a
table at the end of the word document. The table should be
followed by a brief description and source of each variable. You
should put the webpage or document page that each variable
came from.
Do not submit Minitab files. Submit the word proposal
document in the proposal dropbox.
25. Chapter 1: Chapter 1 - X Variable Data Sources
The websites below are the approved sources for your project
independent variable (X) data. They include:
General Economic and Business data--
www.economagic.comwww.nber.orghttp://research.stlouisfed.or
g/fred2/
http://www.economy.com/freelunch
Employment Statistics--www.stats.bls.gov
Population Characteristics data--
http://www.census.gov/popest/estbygeo.html
http://www.census.gov/econ/index.html
Regional Economic Data from the Dallas Federal Reserve Bank-
-
http://dallasfed.org/data/resources.html
Texas Employment and Unemployment data
http://www.tracer2.com/
Make sure to carefully read the project proposal requirements
and the project outline in the Doc Sharing area under the tab at
the top of this screen. Look at the data available in these sites
and decide which data series you wish to select for the X
variables and forecast. Keep in mind that you must find at least
three other related quarterly data series of the same length (and
dates) to help you forecast your primary sales data series. This
means that you will need four data series with the same periods
(quarters) for your project.