Would you conclude that the two groups were significantly different at alpha = .01?
/* H0: mu1 eq mu2 H1: mu1 ne mu2 */ proc iml; start; n1 = 5; n2 = 5; xb1 = {14.2, 9.0}; xb2 = {12.8, 16.2}; x = xb1 - xb2; w = {567.6 215.2, 215.2 96.8}; p = nrow(w); c = (n1 * n2 * (n1 + n2 -2))/(n1 + n2); T2 = c # T(x)*INV(w)*x; print T2; df2 = n1 + n2 - p - 1; c = df2/((n1 + n2 - 2)*p); F = c # T2; print F; print "degrees of freedom = ",p," and ",df2; finish; run;