Question: 1. Suppose that the least squares regression of Yon X1, X2, ..............., XA yields coefficient estimates b1(j = 1, 2, ... , k) none of which exceed their respective standard errors. However, the F-ratio for the equation rejects, at the 0.05 level the hypothesis that b1 = b2 = ... = b, = 0.
(a) Is this possible?
(b) What do you think is the reason for this?
(c) What further analysis would you perform?
2. Explain how you will estimate a linear regression equation which is piecewise linear with a joint (or knot) at x = Xo if
(a) X0 is known.
(b) X0 is unknown.