only claim lesson if you have experience with statgraphics

GROUP PROJECT #3: REGRESSION ANALYSIS

Team Assignment (20 points)

Due: Thursday, 7/20/2017

General Instructions:

1. Work with your assigned team and submit a team report based on the following guidelines.

1. SCENARIO:
   A cable company is interested in understanding what factors explain customers’ satisfaction with their cable television service. A survey is sent to a random selection of customers, and about 100 valid responses are received.

1. Download the Excel data file for the project (BA 376 Grp Proj Data) from Canvas [You’ll need to open statgraphics, then open by selecting File->Open->Open Data Source, choose “External Data File”, then browsing for your excel file].

1. Specific Instructions:

   1. FORMAT:

      1. Your report must be in MSWord format (font: New Times Roman size 11) with reports from StatGraphics/Centurion (cut & paste).

      2. The report must contain exactly 3 pages. Page #1 is the cover sheet. Include your name.

      3. Be sure both team members fully participate. Do not switch groups without instructor approval.

      4. For manual calculations, you may write them, but be neat and concise.

      5. Do not repeat the question or instructions; just number the responses the same as the question.

      6. Supporting graphs and tables should be imbedded within the report; not in an appendix.

   2. STATGRAPHICS:

      1. StatGraphics is required for this project. Use it as much as possible. StatGraphics assistance is provided within the assignment.

      2. Be concise and include only essential Statgraphics results to support your argument.

      3. Show all required calculations—manual calcs and StatGraphics calcs.

      4. Do not include extraneous StatGraphics output; i.e., do not include any Statgraphics printout that you do not know how to interpret.

      5. Do not copy The Stat Advisor into your document!!

      6. Be sure to state your conclusions in your words—don’t just copy the StatGraphics conclusions.

1. 1. GRADE-RELATED ISSUES:

      1. Late projects are not accepted—zero points.

      2. Be sure both team members have reviewed the entire document and understand the contents.

      3. Each team must do its own work. SUBMIT YOUR OWN WORK. Teams are not allowed to work together in any way.

1. YOUR ANALYSIS As stated below, conduct the required analysis and place your answers on the appropriate pages of your report (identified as “Page #x:”); i.e., in the order indicated below ↓ & on these specific pages ↓ .

Page 1: Write a cover page (include your name, the instructor’s name, the date and “Project #3) be sure all participating team members review before submitting. Please be aware that if you did not participate in the project, your score is zero.

Page 2 & 3:

[5] Simple Linear Regression Analysis. Using appropriate StatGraphics output, evaluate whether customers’ evaluation of reliability is a good predictor of customers’ overall satisfaction by conducting the following analyses.
[Hint: Relate—One Factor—Simple Regression]

1. [1] Page #2: Print the scatter diagram and, in a few sentences, discuss what it tells you about these two variables—relationship, strength, how they might be related, etc.

2. [1] Page #2: Write the equation of the “best fit” line representing this data (use all available numbers).

3. [1] Page #2: Use the regression equation developed in (b) to predict a customer’s overall satisfaction given she rated her satisfaction with reliability as a “4”.

4. [1] Page #2: Interpret the meaning of the slope within the context of this problem.

5. [1] Page #2: What is the correlation coefficient? Interpret its meaning.

[5] Multiple Linear Regression Analysis. Using appropriate StatGraphics output, create a good set of predictors of customers’ overall satisfaction by conducting the following analyses.
[Hint: Relate—Multiple Factors—Multiple Regression]

1. [1] Page #3: Perform a regression analysis using “Satisfaction” as your dependent variable and “Price”, “Value”, “Variety”, “Kinds”, “Reliability”, and “Working” as independent variables. Include your output for each parameter, and for the overall ANOVA.

2. [1] Page #3: Comment on each of the p-values on your output. What do they mean?

3. [1] Page #3: Use your model from (f) to predict the satisfaction of a customer who rated “Price” and “Value” at a 4, “Kinds”, “Reliability” and “Variety” as a 5, and “Working” as a 6.

4. [1] Page #3: Now repeat the process in (f) but only include two predictor variables. You may pick any two variables as long as both have “significant” p-values lower than 0.05. Include your output for each parameter, and for the overall ANOVA. Write the equation for this “best fit”.

5. [1] Page #3: Each independent variable of your model should now have a p-value less than 0.05. Is this the only set of independent variables that would work? How do you know?

Food for thought (not graded): Relate your answers to the simple linear regression and the multiple linear regression. How can you reconcile your answer to the simple linear regression fact with the idea of a multiple regression that does not include “reliability” at all?