I have constructed an assignment for my Business Analytics course using the Diamonds data set in the ggplot2 package. Unfortunately, I have just realised that the y-variable, price, is truncated for some reason at about k$18.9 see HERE for a plot. There is nothing in the documentation of this data set that explains its source or the reason for truncation.

I guess I have two questions.

• Is anybody familiar with this data set and the true story for why it is truncated? (I can easily write my own story).
• Is there an standard linear model package that will estimate a regression where the Y-variable has a hard known truncation (let’s assume the observed y is conditional on Y<c). I am kind of embarrassed that I never encountered a truncated regression before