Q1. Consider fitting the simple model y = 3x-, to some data points (T1, y1), . .. , (In, yn). By minimizing the RSS show that the optimal choice of B is B = Linyi (1) (a) Now consider a Ridge regression problem which requires minimizing RSS Ridge = (yi - Ba?)2 + 282. 1= 1 Show that in this case the optimal selection of B is BR = (2) (b) If the true regression function is in the form of f(x) = Bx2 and we measure the noisy observations y = Br' + 6, where e is a random variable with Ec = 0, var(() = o', show that var(BR) = - (c) By setting A = 0 we can immediately see that for the optimal value of B in (1), var() can be calculated as 02 var(B) = show (mathematically or discuss technically) that for all > > 0: var(BR)