More lags
It might be interesting to learn if coupon actions only cause an immediate effect on sales or if the effect continues into the next period.
Again, you shift the COUPON predictor back by using the function lag(). The result is assigned to a new variable Coupon.lag. Both, the original COUPON and the Coupon.lag variables, are added to the log(SALES) ~ PRICE + Price.lag relationship by using the update() function.
This exercise is part of the course
Building Response Models in R
Exercise instructions
- Create a lagged variable for
COUPONnamedCoupon.lag. - Update the
lag.modelobject forCOUPONandCoupon.lagby using the functionupdate().
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
# Take the lag of COUPON
Coupon.lag <- ___
# Update the model for COUPON and Coupon.lag
___(lag.model, . ~ . + ___ + ___)