The following questions will consider the R function: ksmooth

(a) What does this function estimate and what method is used?

Ans: The ksmooth function is a nonparametric regression estimation function that uses a kernel.  

(b) What are your choices of kernels?

Ans: In HW we used the "box" and "normal" kernels. There are other choices.

(c) What is the purpose of the option "bandwidth"?

Ans: The bandwidth changes the length of the "box" or the distance between the
two points of inflection of the "normal" kernal and adjusts the smoothness of
the curve. 

(d) What is the difference in the estimate when a small bandwidth
is used versus a large bandwidth? A plot might be useful.

Ans. See the plots and answers to HW#10 Problem 3 and 4.