Exercise #9

October 10, 2013

Due Tue, Oct 15

Build 2 multiple regression models

Model 1.  Analyzing the Database Problem #4 on page 549. You will need the Excel data that we’ve used previously for database exercises: black_7e_excel_database

Model 2.  Build a multiple regression model with your set of Pueblo Property Data. See instructions below for Model 2.

  • Use the simple “bivariate” regression model developed in Exercise #8.
  • Use your previously completed correlation analysis (see Exercise #7) to identify other key variables that may improve the regression model.
  • Use the Data Analysis ToolPak in Excel to build several multiple regression models (i.e., models with 2 or more independent variables).
  • Save the output from each model run.
  • Choose what you consider to be the best model and write a short paragraph describing why you chose it.

Turn in the following (printed) in class on Tuesday:

  1. Description of Model 1 along with brief answers to questions posed in problem #4 on p. 549
  2. A list of all model runs attempted for Model 2, include (a) the variables used, (b) the model equations and (c) the resulting r-squared values.
  3. List the model you’ve selected and a brief written description as to why you think it’s the best.

Justin

Justin Holman is CEO of Aftermarket Analytics, where he leads efforts to develop cutting edge sales forecasting and inventory optimization technology for the Automotive Aftermarket. Prior to joining Aftermarket Analytics, Justin managed corporate consulting for the Strategy & Analytics division at MapInfo Corporation, leading major projects for retail clients including The Home Depot, Darden Restaurants, Bridgestone-Firestone, Sainsbury’s and New York & Company. Before that, Justin served as Vice President of Software Development at LogicTools, now part of IBM's supply chain application software group. Justin holds a B.A. from Claremont McKenna College, a Ph.D. from the University of Oregon and an Executive Management certificate from Northwestern University's Kellogg School of Management.

1 Comment

  • Reply
    justinholman 11 years ago

    Here’s a question I received from a student via email. I’m posting here to help others who might be stuck:
    “I am trying to complete problem 4 on page 549, and am having trouble knowing how to use the regression analysis.
    I am entering Annual Household Income as the y variable and Non Mortgage household debt as the y variable. However when the model generates, I get a value bigger than 1. What am I doing wrong?”

    Here’s my answer:

    Your dependent variable is y. Dependent means that it needs/depends on x in order to arrive at a corresponding estimated value.
    Your independent variable is x. Independent means that we’re not trying to predict/estimate this value. We only want to use it to predict/estimate something else, that something being the dependent variable. In simple bivariate regression there is only one independent variable. In multiple regression there are 2 or more independent variables.

    So for problem 4:
    Annual Food Expenditure is the dependent variable and should be selected as the y variable.
    Annual Household Income and Non-Mortgage Debt are the independent variables that you will use to estimate Annual Food Expenditure and should be selected as the x variable.

    Try these selections and let me know how it goes. Hope that helps!

Leave a Reply