2 Let b 0, b 1, , b k be the OLS estimates from the regression of yi on xi1, , xik,

2 Let b ˆ 0, b ˆ 1, …, b ˆ k be the OLS estimates from the regression of yi on xi1, …, xik, i51, 2, …, n. For nonzero constants c1, …, ck, argue that the OLS intercept and slopes from the regression of c0 yi on c1xi1, …, ckxik, i 5 1, 2, …, n, are given by b ˜ 0 5 c0 b ˆ 0, b ˜ 1 5 (c0/c1)b ˆ 1, …, b ˜ k 5 (c0/ck)b ˆ k. [Hint: Use the fact that the b ˆ j solve the first order conditions in (3.13), and the b ˜ j must solve the first order conditions involving the rescaled dependent and independent variables.]