Using as the test statistic, we have shown in Section 11.1.4 that the random
variable defined by Equation (11.36) has a t- distribution with n 2 degrees of
freedom. Suppose we wish to achieve a Type-I error probability of. We would
reject H 0 if exceeds (see F igure 11.6)
0
10 20
20
40
60
80
100
120
140
+^x
l 2 (x)
l 1 (x)
Young’s modulus,
y
(g/cm
2 )
Stress,x (g/cm^2 )
^
Figure 11. 5 The 95% confidence band for E Y for Example 11.4
1–
/2 /2
- tn,/2 tn,/2
fT(t)
t
Figure 11. 6 Probability density function of T
352 Fundamentals of Probability and Statistics for Engineers
B^
j ^ 0 j
α β
f g
γ
γ γ
γ γ
"B^ 0 ) c^2 [
Pn
i 1
"xix)^2 ]^1
1/2
,