Be sure you have reviewed documents in the module. I have communicated expectations for how to communicate regression results.

Be sure you have reviewed documents in the module.

I have communicated expectations for how to communicate regression results. FOLLOW THESE EXAMPLES SO THAT YOU CRAFT YOUR CONTENT WELL AND OFFER CLEAR EXPLANATIONS.

See the document on creating tables of regression results and be sure that you have the required elements.
You must discuss BOTH t-tests and p-values to show an understanding of both.
See the document that offers you a model for how to communicate both p-value and t-test results in an efficient manner.
You should go back to previous lectures and be sure you understand dummy and categorical dummy variables, as they will be employed in regression.

NOTE: WHEN RUNNING REGRESSION IN EXCEL, THE VARIABLES IN YOUR MODEL MUST BE NEXT TO EACH OTHER IN ADJACENT COLUMNS. THIS MEANS YOU NEED TO REARRANGE DATA AND POSSIBLY HAVE MORE THAN ONE VERSION OF YOUR DATA SET SO THAT IT MATCHES THE MODELS YOU ARE USING. THIS IS A WEIRD EXCEL QUIRK, UNFORTUNATELY. IF YOU KNOW ANOTHER PROGRAM (R, STATA, SAS, ETC.) YOU MAY USE IT.

************************************************************************************************************************************************************

Overview:

In week 3 you worked with a data set on restaurant sales (173 observations). You will use this data set to perform regression analysis. You will focus on 3 specifications of the model detailed below. In a cohesive and well-organized report, you will perform analysis and discuss findings. You must provide results table(s), in the fashion discussed in the handout on presenting regression results. You will also be asked to reflect on what is not being controlled for that could be important, so that your client understands that there might be some omitted variables causing bias in results.

You will format your discussion in a manner similar to the example provided to you in the module. The quality of your analysis, the quality of your writing, and the professionalism of your report will be factored into your grade. Use the technical writing tips discussed earlier and follow the examples in the handouts of how to set up tables and communicate findings.

NOTE: Before starting, please change variable names as follows (for ease of grading). As you were instructed to do in a previous module, be sure that you have created variables in the affirmative, so SWAM is SWAM YES, where 1=yes and 0=no.

Gross Sales (remember that this is average WEEKLY sales when you interpret)
SWAM
Franchise
Website
Road Frontage
Competitors
Marketing %
Meals Tax
Food Types of American, Asian, Mexican, Italian, Other (one will be the omitted category).
ALSO, ALLOW ME TO MAKE ONE MORE CLARIFICATION BEFORE YOU START. LET’S ASSUME THAT THE AVERAGE WEEKLY SALES IS BEFORE MEALS TAX. IN OTHER WORDS, RESTAURANTS WITH A MEALS TAX WILL NOT HAVE THIS MEALS TAX INFLUENCING THEIR SALES DATA. THIS ALLOWS US TO COMPARE APPLES TO APPLES, IN THIS SENSE. I DO NOT WANT THIS ISSUE TO CAUSE ANY CONFUSION. IT IS TRUE THAT IF OUR SALES DATA REFLECTED THE TAX (FOR SOME RESTAURANTS THAT HAVE THE TAX AND NOT OTHERS), THIS WOULD NOT BE AS CLEAN.

YOU CLIENT WANTS TO SEE WHAT CAN BE LEARNED IN A MORE SOPHISTICATED ANALYSIS, WHICH REGRESSION ALLOWS FOR. THE FOLLOWING 5 THINGS NEED TO BE ADDRESSED IN YOUR REPORT:

A. EXPECTED SIGN:

Create a table providing variable name, definition of each variable, expected sign in regression ( , -, or ?), and the relevant hypothesis test (either one-tailed or two-tailed) for your analysis. This informs the reader about your apriori assumptions and type of test conducted. Be sure to offer some motivation.

B. MODEL 1:

The investors think that weekly average gross sales is potentially impacted by if SWAM, if a franchise, if restaurant has a website, if it has road frontage, if it has a meal tax, # of competitors, % spent on marketing, and type of food (USE AMERICAN AS OMITTED CATEGORY IN YOUR CATEGORICAL VARIABLE). You will perform this analysis and inform the investors of what is learned.

C. MODELS 2A and 2B:

The investors want to know if variables impact average weekly gross sales the same way (in sign and magnitude of effect) when looking at only American food restaurants vs. when looking at only Non-American food restaurants (so looking at all other types of food together as one category). You will perform this analysis and inform the investors of what is learned.

D. MODEL 3:

Expanding on model 1, investors want to know if 2 variables– Number of Competitors

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes:

<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>