I am reading chapter 5 of The Elements of Statistical Learning by Hastie et al. I would like to ask:
- Are the two knots positioned at the two red circles in the top left panel?
- What is the purpose of $h_1(X) = 1$?
- What is the purpose of $h_2(X) = X$?
- Why do we only have $K$ basis functions? For instance with 2 knots, dont we need 3 equations (one for each interval)?
- Can I have an explanation for equation $(5.5)$?
Thank you so much!
