HOA 732 Spring 2026 Midterm Project

1) The datafile All Greens Sales Data.csv shows the following variables:
The data (X1, X2, X3, X4, X5, X6) are for each franchise store.
Y= annual net sales/$1000
X1 = number sq. ft./1000
X2 = inventory/$1000
X3 = amount spent on advertising/$1000
X4 = size of sales district/1000 families
X5 = number of competing stores in district

(a) Fit an MLR model to Y as a function of the potential predictors in the datafile.

(b) Fit Random Forest model to Y as a function of the potential predictors in the datafile.

(c) Compare the two models.


2) The datafile CBC.csv shows the following variables:
Seq# ID# Gender M R F FirstPurch ChildBks             
YouthBks CookBks DoltYBks RefBks ArtBks GeogBks ItalCook
ItalHAtlas ItalArt Florence

(a) Fit a logistic regression model for Florence as a function of the potential predictors in the datafile CBC.csv

(b) Fit a Random Forest model for Florence as a function of the potential predictors in the datafile CBC.csv data.

(c) Compare the two models.