112. Reconsider the situation of Exercise 103, in which x  retained austenite content using a garnet abrasive and yabrasive wear loss were related via the simple linear regression model Y  b0  b1 x  e.

Suppose that for a second type of abrasive, these variables are also related via the simple linear regression model Y  g0  g1 x  e and that V

(e) 

s2 for both types of abrasive. If the data set consists of n1 observations on the rst abrasive and n2 on the second and if SSE1 and SSE2 denote the two error sums of squares, then a pooled estimate of s2 is  (SSE1  SSE2)/(n1  n2  4). Let SSx1 and SSx2 denote for the data on the rst and second abrasives, respectively. A test of H0: b1  g1  0 (equal slopes) is based on the statistic When H0 is true, T has a t distribution with n1 
n2  4 df. Suppose the 15 observations using the alternative abrasive give SSx2  7152.5578, 
.006845, and SSE2  .51350. Using this along with the data of Exercise 103, carry out a test at level .05 to see whether expected change in wear loss associated with a 1% increase in austenite content is identical for the two types of abrasive.