Task 1: Using the equation editor, specify your model.

You must have at least 5 explanatory variables with one of these variables being a dummy variable and at least two explanatory variables being continuous variables.

Task 2: Explain what you are trying to predict and why this model will be useful to you or someone in your industry. Also, explain how you expect your explanatory variables to impact your response variable.

Example: I am building a model to evaluate the factors that impact the home prices in Reno. This model will be useful as a determine a more accurate list price and/or offer price for home. Based on my experience, I believe, on average, homes with more bedrooms and bathrooms will have a higher selling price. Similarly, larger homes and homes on large lots will also have higher selling prices. Lastly, I have included a dummy variable for homes located in Midtown since I believe this location demands higher prices.

Task 3: Specify which variables you should remove and which variables you should keep at the 5% significance level.

Guide: Keep the variables which have p-values less than 0.05 and remove the variables which have p-values greater than 0.05.

OPTIONAL FOR ADDITIONAL FEEDBACK

Task 4: Estimate your reduced variable model based on Task 3. Summarize your results. This summary should contain an interpretation of the coefficients (as x variable increases by 1 unit, y variable increases/decreases by coefficient). Emphasize any results that are surprising (for example: if number of bedrooms had a negative coefficient, I would explain why my results are different than what I expected. Maybe Reno residents prefer less bedrooms that are larger over more, smaller bedrooms).

Task 5: Create a table for your results to match the one included in the Data Analysis Report instructions.

Submission: Submit your excel file with the relevant data and regression results and word document containing tasks 1, 2 and 3 (and tasks 4 and 5 for additional feedback, not required and not graded).