Regression Analysis Assignment
Data
The multiple regression
assignment can be done individually or in a team of up to three students.
You or your team
should gather data on a dependent variable and
independent variables that are of interest to you,
subject to the following limitations:
- There should be at
least 30 observations in your data set.
- The data can be
either cross-section or time series.
- There must be some logical reason for the number
of observations that you choose.
Ex. - If you
are using data for states, use all 50 states in the United States.
Ex. - If you
are using data for the developing countries of Asia, you should use data for
all 41 countries who are members of the Asian Development Bank.
Ex. - If you
are using quarterly data, you should use data for
eight years (32 quarters).
Ex. - If you
are using monthly data, you should use data for three
years (36 months).
However, it is
appropriate to start at the beginning of a year and
end with the most recent data:
Ex. - 2002 Q1 to
2009 Q3 = 31 quarters
- The minimum number of
independent variables in your model should be three if you are
working on your own, four if you are working in a team of two, and
six if working in a team of three.
- At least one of the
independent variables must be a dummy variable.
- No more than half of
the independent variables can be dummy variables.
- Do not use the data
from the marketing survey.
Analysis
Use your data and a
spreadsheet program to do to perform a multiple
regression analysis for your variables. The analysis
should include the following:
- Provide a brief background of the
situation you are going to look at. Specifically, why is your
dependent variable interesting or significant? Indicate the general model that you are
going to estimate. Discuss what you think the
relationship is between the dependent variable
and the independent variables, and what that
leads you to conclude about the expected signs of
the coefficients in the model. Determine the correlation
between each of the independent variables and the dependent
variable.
- Present the estimated model. Give an
interpretation of the coefficient of
determination (r2). List the adjusted r2.
Use the F-test to test the validity of the model as a whole at
a 5% level of significance.
- Give an
interpretation of each of the estimated
coefficients. Do the signs of the coefficients
match your expectations? At the 5% level of significance, test whether each of the
variables makes a significant contribution to the model .
- Conduct an analysis
to determine if any problems exist.
- Summarize the results of your
analysis. Use your model to
make a prediction for any combination of values
for your independent variables.
- Include the computer results in the form of an
appendix.
Final Output
Please submit a copy of
your analysis in the form of a report by Friday, January 22, but that
date is flexible. If the output is a hard copy, it should be
printed on 8 ½ x 11 or A4 paper. Please do not submit the
report in a special report cover; a stable in the upper
left hand corner would be adequate. The output may also
be submitted as an e-mail attachment.
|
