Create future predictor variables
To get forecasts for the regression models with price, holidays, and promotions we need future values for each of these inputs! For our high end product we previously determined holidays and promotions aren't important to the model. Prices are negotiated 6 months in advance, so the prices in the validation data set are reasonable to use for forecast calculations. Your validation data set is stored in your workspace as bev_xts_valid
.
This exercise is part of the course
Forecasting Product Demand in R
Exercise instructions
- Store the log of the prices (stored as the variable
MET.hi.p
) from your validation data set as a vector usingas.vector()
. - Create a validation data frame using
l_MET_hi_p_valid
and set the column names using the provided code.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Subset the validation prices #
l_MET_hi_p_valid <- as.vector(___(bev_xts_valid[,"___"]))
# Create a validation data frame #
MET_hi_valid <- data.frame(___)
colnames(MET_hi_valid) <- "log_price"