Predict shares for chocolate bars
Suppose a store plans to carry Ghiradelli chocolate in all 5 types. What will the shares be between these five chocolates? The store may want to know this so that they can plan their inventory or re-arrange the display to feature the most popular chocolate types.
The chocolate
dataset is pre-loaded for you as an mlogit.data
object.
This exercise is part of the course
Choice Modeling for Marketing in R
Exercise instructions
- Fit the
choc_m2
model usingmlogit
. The first input should be the formulaSelection ~ 0 + Brand + Type + Price
and the second should bedata = chocolate
. - Create a data frame that includes 5 chocolate bars that are all
Ghirardelli
and all priced at $3. The types should be the five types that were tested in thechocolate
data. I've started the code for you. You just need to finish defining the prices. - Predict shares using my
predict_mnl()
function, which is already loaded.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# fit the choc_m2 model
# create a data frame with the Ghiradelli products
Brand <- factor(rep("Ghirardelli", 5), level = levels(chocolate$Brand))
Type <- levels(chocolate$Type)
Price <- _____ # treated as a number in choc_m2
ghir_choc <- data.frame(Brand, Type, Price)
# predict shares