Regression for holiday / promotional effects
Now that you have created the New Year's indicator variable, let's see if it is significantly different than the usual sales pattern using regression.
Your data.frame
with log of sales and log of prices is saved in your workspace as MET_hi_train
. Your New Year's variable is stored as newyear
.
This exercise is part of the course
Forecasting Product Demand in R
Exercise instructions
- Create a new dataset,
MET_hi_train_2
by combiningMET_hi_train
and your new year variable as a vector. - Build a regression model for the high end product in the metropolitan region. The model should predict the log of sales (
log_sales
) with the log of price (log_price
) and the New Year's variable (newyear
) and use the newMET_hi_train_2
dataset you just created.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Create MET_hi_train_2 by adding newyear
MET_hi_train_2 <- data.frame(MET_hi_train, as.vector(___))
colnames(MET_hi_train_2)[3] <- "newyear"
# Build regressions for the product
model_MET_hi_full <- lm(___ ~ ___ + ___, data = ___)