Using the non-parametric bootstrap, find an estimator for the variance of mb (0.5). Provide all your working. Solution: Generate a bootstrap sample (x ? i , y? i ) n i=1 by sampling with replacement from (xi , yi) n i=1. Repeat B times to get ( m?(b) ) B b=1, and compute the sample variance of the {m ?(b) (0.5)}. This gives V ar( m(0.5)) V ar{m ?(b) (0.5)} = 0.002