Refer to the previous exercise. When we add an interaction term, we get y = 16.6 +

Refer to the previous exercise. When we add an interaction term, we get ˆy = −16.6 + 66.6x1 − 31.8x2 +

29.4(x1x2).

(a) Interpret the fit by reporting the prediction equation between selling price and size of house separately for new homes (x2 = 1) and for old homes (x2 = 0). Interpret.

(This fit is equivalent to fitting lines separately to the data for new homes and for old homes.)

(b) Aplot of the data shows an outlier, a new home with a very high selling price.When that observation is removed from the data set and the model is refitted, ˆy = −16.6 +

66.6x1 + 9.0x2 + 5.0(x1x2). Redo (a), and explain how an outlier can have a large impact on a regression analysis.